Guided Project: Analyzing Wikipedia Pages
Posted on Wed 08 July 2015 in Projects
Introducing Wikipedia Data¶
In [2]:
import os
os.listdir("wiki")
Out[2]:
['%C3%81lvaro_Sierra.html', '%C3%89cole_des_Mines_de_Douai.html', '%C3%89taule.html', '%C3%96lm%C3%BCs_bir_kadinin_evraki_metrukesi.html', '%C5%81osie-Do%C5%82%C4%99gi.html', '%C5%8Cnog%C5%8D_Station.html', '%C5%9Eah%C3%AEn%C3%AA_Bekir%C3%AA_Sorekl%C3%AE.html', '(1-4)-a-D-glucan_1-a-D-glucosylmutase.html', '1._FC_Eschborn.html', '100%25_Banco.html', '100_Greatest_Romanians.html', '100_mm_field_gun_M1944_(BS-3).html', '104th_Logistic_Support_Brigade_(United_Kingdom).html', '1208_(band).html', '125th_(Lancashire_Fusiliers)_Brigade.html', '16th_Virginia_Infantry.html', '1860_in_science.html', '1866_in_birding_and_ornithology.html', '1879_FA_Cup_Final.html', '1896_Indiana_Hoosiers_football_team.html', '1898_Colgate_football_team.html', '1904_Case_football_team.html', '1905%E2%80%9306_FC_Barcelona_season.html', '1910_in_literature.html', '1915_Montana_football_team.html', '1937_Social_Credit_backbenchers%27_revolt.html', '1947_Notre_Dame_Fighting_Irish_football_team.html', '1951_National_League_tie-breaker_series.html', '1953%E2%80%9354_FA_Cup_qualifying_rounds.html', '1958_Wightman_Cup.html', '1963_Pittsburgh_Panthers_football_team.html', '1968_Duke_Blue_Devils_football_team.html', '1970_African_Cup_of_Nations.html', '1975%E2%80%9376_FIBA_Kora%C4%87_Cup.html', '1976_Kansas_State_Wildcats_football_team.html', '1978_College_Football_All-America_Team.html', '1982_Kentucky_Derby.html', '1982_World_Series.html', '1984%E2%80%9385_Southern_Football_League.html', '1984_WAC_Men%27s_Basketball_Tournament.html', '1987_Football_League_Trophy_Final.html', '1988_Chatham_Cup.html', '1988_State_of_Origin_series.html', '1989_Preakness_Stakes.html', '1990%E2%80%9391_Southern_Football_League.html', '1991%E2%80%9392_BHL_season.html', '1991_RTHK_Top_10_Gold_Songs_Awards.html', '1991_uprising_in_Basra.html', '1991_US_Open_%E2%80%93_Women%27s_Doubles.html', '1992_European_Athletics_Indoor_Championships.html', '1994_French_Open_%E2%80%93_Men%27s_Doubles.html', '1994_Scotland_rugby_union_tour_of_Argentina.html', '1995_FINA_Men%27s_Water_Polo_World_Cup.html', '1996_UEFA_Futsal_Championship.html', '1997_Edmonton_Eskimos_season.html', '1999%E2%80%932000_UEFA_Champions_League_second_group_stage.html', '1999_Caribbean_Cup.html', '1999_MTV_Video_Music_Awards.html', '1st_Strategic_Aerospace_Division.html', '2000_Pepsi_Southern_500.html', '2001%E2%80%9302_NBA_season.html', '2001_Australian_Individual_Speedway_Championship.html', '2001_Copa_del_Rey_Final.html', '2001_NCAA_Division_I_Field_Hockey_Championship.html', '2002%E2%80%9303_Scottish_Second_Division.html', '2003_World_Championships_in_Athletics_%E2%80%93_Women%27s_hammer_throw.html', '2004_Tuvalu_A-Division.html', '2005%E2%80%9306_in_Welsh_football.html', '2005_Asian_Women%27s_Club_Volleyball_Championship.html', '2005_in_radio.html', '2005_NCAA_Division_I_Men%27s_Basketball_Tournament.html', '2006_European_Athletics_Championships_%E2%80%93_Women%27s_triple_jump.html', '2007%E2%80%9308_Huddersfield_Town_A.F.C._season.html', '2007%E2%80%9308_Women%27s_EHF_Cup.html', '2007_in_Belgian_television.html', '2007_Kilkenny_Senior_Hurling_Championship.html', '2008_2._deild_karla.html', '2008_Fed_Cup_World_Group_II.html', '2008_Swedish_Open.html', '2009_English_cricket_season.html', '2009_European_Junior_Swimming_Championships.html', '2009_Giro_di_Lombardia.html', '2009_Open_Costa_Adeje_%E2%80%93_Isla_de_Tenerife_%E2%80%93_Singles.html', '2009_World_Junior_Ice_Hockey_Championships_rosters.html', '2010_Karshi_Challenger_%E2%80%93_Singles.html', '2010_New_Year%27s_Eve_tornado_outbreak.html', '2011%E2%80%9312_Western_Collegiate_Hockey_Association_women%27s_ice_hockey_season.html', '2011_Dutch_National_Track_Championships_%E2%80%93_Men%27s_1_km_time_trial.html', '2011_ITU_Duathlon_World_Championships.html', '2011_Mosconi_Cup.html', '2011_UK_Open_Qualifier_4.html', '2011_Wainwright_Roaming_Buffalo_Classic.html', '2012%E2%80%9313_Liga_Na%C8%9Bional%C4%83_(women%27s_handball).html', '2012%E2%80%9313_SVB_Hoofdklasse.html', '2013%E2%80%9314_Stirling_%26_District_Amateur_Football_Association.html', '2013_Curlers_Corner_Autumn_Gold_Curling_Classic.html', '2013_FIA_WTCC_Race_of_Russia.html', '2013_Mississippi_State_Bulldogs_baseball_team.html', '2013_San_Luis_Open_Challenger_%E2%80%93_Doubles.html', '2013_World_Grand_Prix_(darts).html', '2014%E2%80%9315_Albanian_Third_Division.html', '2014%E2%80%9315_Kansas_State_Wildcats_men%27s_basketball_team.html', '2014%E2%80%9316_European_Nations_Cup_Second_Division.html', '2014_Kano_bombing.html', '2014_Special_Honours.html', '2014_World_RX_of_Turkey.html', '2015%E2%80%9316_PLK_season.html', '2015%E2%80%9316_Washington_Huskies_men%27s_basketball_team.html', '2015_NWSL_College_Draft.html', '2015_Thai_League_Cup.html', '2016%E2%80%9317_Little_Rock_Trojans_women%27s_basketball_team.html', '2016%E2%80%9317_New_Zealand_Football_Championship.html', '2016_Danmark_Rundt.html', '2016_FK_Haugesund_season.html', '2016_Minnesota_Vikings_season.html', '2017_Orange_County_Breakers_season.html', '23rd_Reserve_Battalion,_CEF.html', '24th_Genie_Awards.html', '25B-NBOMe.html', '26th_Illinois_Volunteer_Infantry_Regiment.html', '3-(Trifluoromethyl)aniline.html', '33rd_New_Jersey_Volunteer_Infantry.html', '427.html', '4_Way_Street.html', '50_caliber_Mark_7_gun.html', '55th_parallel_south.html', '59th_Oza.html', '83_(number).html', '877_Naval_Air_Squadron.html', '985_Innovative_Platforms_for_Key_Disciplines_Project.html', 'A%C3%A9ro_Services_Gu%C3%A9pard_Gu%C3%A9pard_912.html', 'A._P._Komala.html', 'A_Beautiful_Valley.html', 'A_Month_of_Sundays_(miniseries).html', 'A_Slow_Messe.html', 'A_Sport_and_a_Pastime.html', 'Aaron_Paul.html', 'Aaron_Williams_and_the_Hoodoo.html', 'Aaronsburg_Historic_District.html', 'Aattanayagann.html', 'AAU_Junior_Olympic_Games.html', 'AB_v_CD.html', 'Abanycha_bicolor.html', 'Abbas_Jadidi.html', 'Abbeville_Sluggers.html', 'Abdelwahid_Aboud_Mackaye.html', 'Abdulla_Majid_Al_Naimi.html', 'Abdulrahman_al-Awlaki.html', 'Abortion_in_Italy.html', 'Abortion_in_Oklahoma.html', 'Abou_Redis.html', 'Abraham_Booth.html', 'Abraham_Stanyan.html', 'Absolutely_Zippo.html', 'Abu_Oleymeh,_Ramshir.html', 'Abyssobela_atoxica.html', 'Acacia_dermatophylla.html', 'Academic_grading_in_Bosnia_and_Herzegovina.html', 'Acceptance_(Heroes).html', 'Acceptilation.html', 'Accommodation_bridge.html', 'Achaea_faber.html', 'Acharapakkam_(State_Assembly_Constituency).html', 'Achim_Schwarze.html', 'ACM_Transactions_on_Computational_Biology_and_Bioinformatics.html', 'Acrocercops_calycophthalma.html', 'Acrolophus_simulatus.html', 'Adelaide%E2%80%93Darwin_railway.html', 'Adios_(B%C3%B6hse_Onkelz_album).html', 'Adish_Aggarwala.html', 'ADNI.html', 'Adolf%C3%B3w,_%C5%81%C3%B3d%C5%BA_Voivodeship.html', 'Adolf_Schulte.html', 'Adoration_of_the_Magi_(Filippino_Lippi).html', 'Adrian_Bawtree.html', 'Adrian_Clarke_(footballer).html', 'Aechmea_%27Pica%27.html', 'Agaritine_gamma-glutamyltransferase.html', 'Agesarchus_of_Tritaea.html', 'Agnes_Tait.html', 'Agnolin.html', 'Agostino_Gemelli.html', 'Agripina_Samper_Agudelo.html', 'Agullent.html', 'Agyneta_allosubtilis.html', 'Ahanta_West_District.html', 'Ahmad_Khatami_(professor).html', 'AIM_Phoneline.html', 'Air_Barons.html', 'Aiva.html', 'Ajminal.html', 'Aku_Partanen.html', 'Al-Midan.html', 'Al-Nurayn_Mosque.html', 'Al_Azim_Mosque.html', 'Al_Mahon.html', 'Al_Sherman.html', 'Alan_Oakley.html', 'Alan_Orr.html', 'Alan_Sheehan.html', 'Albanians_in_Egypt.html', 'Albert_French.html', 'Album-equivalent_unit.html', 'Aldona_Orman.html', 'Aleksandra_Jagie%C5%82o.html', 'Aleksei_Lazarev.html', 'Alex_Karalexis.html', 'Alex_Kurtzman.html', 'Alex_McEachern.html', 'Alexander_Armstrong_(explorer).html', 'Alexander_King_(author).html', 'Alexander_McCue.html', 'Alexander_Rizzoni.html', 'Alexandru_Greab.html', 'Alexei_Vinogradov.html', 'Alexios_Aspietes.html', 'Alexis_Lloyd.html', 'Ali_Al_Bulaihi.html', 'Aliabad-e_Robat.html', 'Alireza_JJ.html', 'Alisa_(soap_opera).html', 'All-Polish_Youth.html', 'All_Ceylon_Tamil_Congress.html', 'All_Lights_Fucked_on_the_Hairy_Amp_Drooling.html', 'All_Tangled_Up_in_Love.html', 'All_the_Fun.html', 'All_You_Get_from_Love_Is_a_Love_Song.html', 'Allama_Iqbal_Medical_College.html', 'Allan_Egolf.html', 'Allan_Lister_Samuel_Brown.html', 'Allen_Snyder_(lawyer).html', 'Alnwick_District_Council_election,_2007.html', 'Alojz_Knafelc.html', 'Alpine_skiing_at_the_1994_Winter_Olympics_%E2%80%93_Men%27s_combined.html', 'Amanda_Peet.html', 'Amano_Artisan_Chocolate.html', 'Amber_Butchart.html', 'Amborella.html', 'AMD_XGP.html', 'Ameenapuram.html', 'American_Federation_of_Labor_Building.html', 'American_Journal_of_Kidney_Diseases.html', 'Aminonaphthalenesulfonic_acids.html', 'Amorphogynia.html', 'Ampelasia.html', 'Amphidromia.html', 'Amy_Watkins.html', 'Ana_Beatriz.html', 'Anatolii_Sloiko.html', 'Ancita_antennata.html', 'Ancylostoma_duodenale.html', 'Anders_Ahlgren.html', 'Andrei_Gamalyan.html', 'Andrew_McNally.html', 'Andrew_S._Tanenbaum.html', 'Andrew_Wilson_(classical_archaeologist).html', 'Angelic_non-determinism.html', 'Angolan_Union_for_Peace,_Democracy_and_Development.html', 'Aniavan.html', 'Anish_Giri.html', 'Anjada_Gandu.html', 'Anne_Whateley.html', 'Annopole_Stare.html', 'Annunciation_Church,_Walsall.html', 'Ant%C3%B3nio_Maria_Baptista.html', 'Ant%C3%B3nio_Marinho_e_Pinto.html', 'Antae_temple.html', 'Anthony_Cesario.html', 'Anthony_Marten.html', 'Antibiotic_use_in_livestock.html', 'Antigonadotropin.html', 'Antipater_of_Thessalonica.html', 'Antoine_Gakeme.html', 'Anton_von_Troeltsch.html', 'Antonio_Ciano.html', 'Antonio_de_Zayas_(bishop).html', 'Anuradhapura_West_Electoral_District.html', 'Apache_Bloodhound.html', 'Aphonopelma_chiricahua.html', 'Apocephalus_borealis.html', 'Appa_(film).html', 'Aq_Dash,_East_Azerbaijan.html', 'Aquaphobia.html', 'ARA_Garibaldi.html', 'Arabic_Toilers%27_Movement.html', 'Arcadio_Gonz%C3%A1lez.html', 'Archibald_Gordon_(British_Army_officer).html', 'Archiepiscopal_Palace,_Rouen.html', 'Area_code_218.html', 'Area_of_refuge.html', 'Argentina_at_the_2015_World_Championships_in_Athletics.html', 'Arkansas_gubernatorial_election,_1968.html', 'Arkansas_Highway_178.html', 'Arnold_Freiherr_von_Biegeleben.html', 'Arrest_warrant.html', 'Arrondissements_of_the_Yvelines_department.html', 'Art_collection_of_Fondazione_Cassa_di_Risparmio_di_Perugia.html', 'Arthur_Baldwinson.html', 'Arthur_L._Aidala.html', 'Arthur_Lelyveld.html', 'Arthur_Mendes.html', 'Arthur_Norman.html', 'Arturo_Liebstein.html', 'Arun_K._Pati.html', 'Arvind_Gokhale.html', 'Ash_Rees.html', 'Asheqlu.html', 'Ashley,_Wisconsin.html', 'Ashu_Dani.html', 'Asparuh_Peak.html', 'Assegaaibosch_Nature_Reserve.html', 'Asun_Balzola.html', 'Athletics_at_the_1994_Commonwealth_Games_%E2%80%93_Men%27s_pole_vault.html', 'Athletics_at_the_2007_Games_of_the_Small_States_of_Europe.html', 'Athletics_at_the_2012_Summer_Paralympics_%E2%80%93_Women%27s_200_metres_T36.html', 'Atlanta_Area_School_for_the_Deaf.html', 'Atlantic_Studios.html', 'Atractaspis_duerdeni.html', 'Atrypanius_scitulus.html', 'Attila,_Illinois.html', 'Aubrey_Fair.html', 'Audefroi_le_Bastart.html', 'August_Duranowski.html', 'Augustine_Chacon.html', 'Austral_Alien.html', 'Australian_federal_election,_1954.html', 'Australian_hardcore.html', 'Australian_Musician_(magazine).html', 'Australiteuthis_aldrichi.html', 'Avalara.html', 'Avengers_Academy.html', 'Avenira.html', 'AVM_GmbH.html', 'Avyarud.html', 'Awali.html', 'Axel_Revold.html', 'Ayish_Bayou.html', 'Aylon_Darwin_Tavella.html', 'Ayodhya_Mandapam.html', 'Baadj.html', 'Baadshah_(1999_film).html', 'Bad_Axe_River.html', 'Bad_Luck_(Social_Distortion_song).html', 'Baddiewinkle.html', 'Bagrat_VI_of_Georgia.html', 'Bahia_bigelovii.html', 'Bahmanabad-e_Olya.html', 'Baigts-de-B%C3%A9arn.html', 'Baithakata_College.html', 'Bal%C3%A1zs_Vill%C3%A1m.html', 'Ballard_Memorial_High_School.html', 'Ballonet.html', 'Balloon_light.html', 'Baltic_Peak.html', 'Ban_On.html', 'Bandar_Botanik_LRT_Station.html', 'Banovina_of_Croatia.html', 'Bar_One_Racing_Juvenile_Hurdle.html', 'Baraf.html', 'Barbara_McKinzie.html', 'Barbus_caudosignatus.html', 'Baritius_cyclozonata.html', 'Barn.html', 'Barnsdall_Art_Park.html', 'Barra_do_Rocha.html', 'Barren_vegetation.html', 'Bart_van_Leeuwen.html', 'Bartrum_Glacier.html', 'Batfink.html', 'Battle_of_Abydos.html', 'Battle_of_Finta.html', 'Battle_of_Isonzo_(489).html', 'Battle_of_Sulukh.html', 'Battle_of_Wattignies.html', 'Battleford-Cut_Knife.html', 'Bawdrip_Halt_railway_station.html', 'Bay_of_Concepci%C3%B3n.html', 'Bayandalai,_%C3%96mn%C3%B6govi.html', 'Bazemore,_Alabama.html', 'BBCH-scale_(rice).html', 'BBG_Academy.html', 'Be%C5%82chat%C3%B3w_Power_Station.html', 'Beaubassin_East,_New_Brunswick.html', 'Beaune_Altarpiece.html', 'Beaupr%C3%A9,_Quebec.html', 'Bebearia_romboutsi.html', 'Bechdel_test.html', 'Bed_and_Breakfast_(album).html', 'Begin_(Riyu_Kosaka_album).html', 'Beijing_Dongyue_Temple.html', 'Belgium_women%27s_national_field_hockey_team.html', 'Beli_language_(South_Sudan).html', 'Bellanca_28-92.html', 'Belmont_Estate.html', 'Belosavci.html', 'Belvedere,_London.html', 'Belvedere_Park,_Georgia.html', 'Ben_H._Williams.html', 'Ben_Rimalower.html', 'Bengt_Forsberg.html', 'Benidorm_Bastards.html', 'Benktander_type_II_distribution.html', 'Benny_Lee.html', 'Bernard-Augustin_Conroy.html', 'Bert_Leboe.html', 'Bertilda_Samper_Acosta.html', 'Berzeliustinden.html', 'Bethoncourt.html', 'Beverley_Hills_Apartment_Block.html', 'Beyond_Magnetic.html', 'Bhimnagar,_Supaul.html', 'Bhubanananda_Das.html', 'Bianna_Golodryga.html', 'Bias.html', 'Bibiana_Beglau.html', 'Bibliography_of_Niue.html', 'Bicycle_basket.html', 'Bifidocarpus.html', 'Bijou,_California.html', 'Bilan_d%27aptitude_d%C3%A9livr%C3%A9_par_les_grandes_%C3%A9coles.html', 'Bill_Overstreet.html', 'Bill_Price_(baseball).html', 'Bill_Widenhouse.html', 'Bill_Williamson_(footballer).html', 'Billi%C3%A8me.html', 'Billy_Grammer.html', 'Billy_McNeill.html', 'Biorock.html', 'Bishop_of_Kingston.html', 'Biz_Kid$.html', 'Black_Moshannon_State_Park_Historic_Districts.html', 'Black_Pond_Township,_Oregon_County,_Missouri.html', 'Blackshear_Prison.html', 'Blick_nach_Rechts.html', 'Blohm.html', 'Blomheller_Station.html', 'Blommersia.html', 'Blue_Heelers_(season_8).html', 'Blue_Sky_Mining.html', 'Blue_SWAT.html', 'Bluesin%27_Around.html', 'Board_of_Jewish_Education_(Toronto).html', 'Boardman_Township,_Mahoning_County,_Ohio.html', 'Bob_Allen_(shortstop).html', 'Bob_Bass.html', 'Bob_Lustig.html', 'Bobo_Sikorski.html', 'Bon_Accord_Free_Church.html', 'Bone_morphogenetic_protein_4.html', 'Bones_Apart.html', 'Bonny_River.html', 'Boogie_Bunnies.html', 'Boone_Square.html', 'Boothapandi.html', 'Botswana_passport.html', 'Bowie_Race_Track.html', 'Bowlers%27_Club_of_New_South_Wales.html', 'Boynton_baronets.html', 'Br%C3%A9zina_District.html', 'Brachylogus.html', 'Brady_Hicks.html', 'Braille_pattern_dots-126.html', 'Branko_Maru%C5%A1i%C4%8D.html', 'Brede_Waterworks.html', 'Brendan_Foster.html', 'Brian_Collins_(2010s_singer).html', 'Brian_G._W._Manning.html', 'Brian_Sims.html', 'Brightside_Apartments.html', 'British_Academy_Television_Award_for_Best_Comedy_(Programme_or_Series).html', 'Bro_Safari.html', 'Brograve_Mill.html', 'Brownfield_(software_development).html', 'Bruce_Conte.html', 'Bruce_Lyon.html', 'Bryan_Payton.html', 'Bryzg%C3%B3w.html', 'Buchanan_%26_Press.html', 'Buffington_Township,_Indiana_County,_Pennsylvania.html', 'Buford,_North_Dakota.html', 'Buko_pie.html', 'Bukovica_(Cazin).html', 'Bulbonaricus.html', 'Bulbophyllum_biflorum.html', 'Burbridge_Creek.html', 'Burmese_shrike.html', 'Burnin%27_Sneakers.html', 'Burnley_(surname).html', 'Burnley_Borough_Council_election,_2011.html', 'Burrough_Court.html', 'Busan%E2%80%93Gimhae_Light_Rail_Transit_Operation_Corporation.html', 'Business.com.html', 'BW_Vulpeculae.html', 'Bycz,_Kuyavian-Pomeranian_Voivodeship.html', 'Bye!_My_Boy!.html', 'Bye_Bye_Mon_Cowboy.html', 'C%27est_la_vie_(Khaled_song).html', 'C%C3%AA.html', 'C10H8.html', 'C11orf30.html', 'C18H23NO6.html', 'Cabrini%E2%80%93Green,_Chicago.html', 'Caladenia_amoena.html', 'Caldelas,_Sequeiros_e_Paranhos.html', 'California_Historical_Landmarks_in_San_Bernardino_County,_California.html', 'California_roach.html', 'California_Unfair_Competition_Law.html', 'Calin_Rovinescu.html', 'Calvin_Harrell.html', 'Camp_Liberty_killings.html', 'Camp_Nelson_Confederate_Cemetery.html', 'Campus_of_Texas_A%26M_University.html', 'Canada_Bay.html', 'Canbelego_County.html', 'Caney_Creek_(Matagorda_Bay).html', 'Cannabis_in_Spain.html', 'Canyamars.html', 'Cape_Bonavista.html', 'Cape_Mayo.html', 'Cappella_San_Donato,_Venafro.html', 'Capriccio_Italien.html', 'Caprinia_versicolor.html', 'Caramel_Box_Yarukibako.html', 'Cardinals_created_by_Alexander_VIII.html', 'Cardipeltis.html', 'Carley_State_Park.html', 'Carlos_Martins_(musician).html', 'Carmen_Weber.html', 'Carroll_O._Switzer.html', 'Carrollwood_Day_School.html', 'Carte_Imagine%27R.html', 'Carthage,_Cincinnati.html', 'Caryl_Nowson.html', 'Cascade_Summit,_Oregon.html', 'Cascate_del_Rio_Verde.html', 'Caste_system_in_India.html', 'Castle_of_Cardona.html', 'Catlett_House_(Staunton,_Virginia).html', 'CCL8.html', 'CDC42EP3.html', 'Cechenena_sperlingi.html', 'Cecil,_Oregon.html', 'Cecil_Biggs.html', 'Cecil_Bothwell.html', 'Cecil_Peak.html', 'Cecile_of_Baux.html', 'Cecyl%C3%B3wka-Brz%C3%B3zka.html', 'Celebrity_doll.html', 'Celta_de_Vigo_B.html', 'Center_(group_theory).html', 'Central_District_(Rezvanshahr_County).html', 'Central_Luzon.html', 'Central_Park_(Tolyatti).html', 'Centzon_Totochtin.html', 'Ceryx_hageni.html', 'Ch%C3%A2telet_surface.html', 'Ch%C3%A9nens.html', 'Chadefaudiellaceae.html', 'Chah-e_Zakaria.html', 'Challenger_Banque_Nationale_de_Drummondville.html', 'Channel_48_digital_TV_stations_in_the_United_States.html', 'Chapel_of_Mercy,_Monaco-Ville.html', 'Charalampos_Brilakis.html', 'Charged_Records.html', 'Charles_Golding_Constable.html', 'Charles_Micallef.html', 'Charles_Page_(cricketer).html', 'Charles_S._Benton.html', 'Charles_Sears.html', 'Charles_Smith_Wilcox.html', 'Charles_Stuart_(rugby_union).html', 'Charles_Trudeau_(politician).html', 'Charles_Wadsworth.html', 'Charlton_baronets.html', 'Chaun_Thompson.html', 'Checkerspot_(magazine).html', 'Cheddar_Ales.html', 'Chef_Wan.html', 'Chemin_d%27Aylmer.html', 'Cherechiu.html', 'Cheryl_Prewitt.html', 'Chester_Morris.html', 'Chestnut_pie.html', 'Chhaparband_(Muslim).html', 'Chhatrasal.html', 'Chicoreus_cervicornis.html', 'Chief_Justice_of_New_Zealand.html', 'Chihuahuan_Desert_Nature_Center_and_Botanical_Gardens.html', 'Chilango_(magazine).html', 'Children_of_Air_India.html', 'Children_of_the_Grave.html', 'Chile_de_%C3%A1rbol.html', 'Chilo_auricilius.html', 'Chinlone.html', 'Chionodes_retiniella.html', 'Chiriguelo.html', 'Chisocheton_cumingianus_subsp._kinabaluensis.html', 'Chocolate_Factory.html', 'Choseng_Trungpa.html', 'Christia_Mercer.html', 'Christian_Amoroso.html', 'Christian_Jessen.html', 'Christianity_and_antisemitism.html', 'Christine_Gardner.html', 'Christopher_Speer.html', 'Chromis_iomelas.html', 'Church_of_St_Mary_the_Virgin,_Keysoe.html', 'Church_of_the_SubGenius.html', 'CIE_1964_color_space.html', 'Circle_Repertory_Company.html', 'Circus_Avenue.html', 'Cisy,_Byt%C3%B3w_County.html', 'Cit%C3%A9_du_Vin.html', 'City_of_Mandaluyong_Science_High_School.html', 'Claire_Danes.html', 'Clarinet_Quintet_(T%C3%A4glichsbeck).html', 'Clarksville,_Pennsylvania.html', 'Class_C_GPCR.html', 'Claude%27s_syndrome.html', 'Claude-Godefroy_Coquart.html', 'Claude_Mandil.html', 'Claudia_Neidig.html', 'Clay_Research_Award.html', 'Clay_Township,_Clark_County,_Missouri.html', 'Clear_Creek_Township,_Cooper_County,_Missouri.html', 'Cleveland,_Oklahoma.html', 'Cleveland_Institution_of_Engineers.html', 'Cleveland_Play_House.html', 'Clinton_Engineer_Works.html', 'Clive_Brown_(footballer).html', 'Clocking_Out_Is_for_Suckers.html', 'Clothes_Show_Live.html', 'Coalition_for_Unity_and_Democracy.html', 'Coalville_Town_railway_station.html', 'Coastal_upwelling_of_the_South_Eastern_Arabian_Sea.html', 'Cobble_Hill,_Brooklyn.html', 'Coble_hypersurface.html', 'Code_page_1023.html', 'Coenaculum_secundum.html', 'Col_Pearce.html', 'Colantonio_Incorporated.html', 'Colchester_Village_Historic_District.html', 'Cole_Shade_Sule.html', 'Colleen_Haskell.html', 'Colors_for_Trombone.html', 'Colossal_Titan_Strife.html', 'Colosseum_LiveS_%E2%80%93_The_Reunion_Concerts.html', 'Columbia_Airport_(Ohio).html', 'Comedy_Now!.html', 'Comisi%C3%B3n_Femenil_Mexicana_Nacional.html', 'Common_Sense_Revolution.html', 'Communities_of_Tulu_Nadu.html', 'Companys,_proc%C3%A9s_a_Catalunya.html', 'Compton%27s_Most_Wanted_discography.html', 'Computational_Geometry_(journal).html', 'Congregation_Agudath_Achim.html', 'Conjugate_depth.html', 'Connecticut_House_of_Representatives.html', 'Connell_Mansion.html', 'Consolidated_Commodore.html', 'Constance_D%27Arcy_Mackay.html', 'Constantin_Ro%C8%99u.html', 'Constitution_of_Kyrgyzstan.html', 'Continuity_of_Operations.html', 'Coosa_County_School_District.html', 'Copamyntis_infusella.html', 'Copenhagen_Skatepark.html', 'Copier_family.html', 'Corey_Lee.html', 'Cornix.html', 'Coronium_(gastropod).html', 'Coronoid_process_of_the_ulna.html', 'Corozal_Hospital.html', 'Corporation_(university).html', 'Corredores_Ferroviarios.html', 'Cortile_del_Belvedere.html', 'Cosmopterix_similis.html', 'Coup_d%27%C3%A9tat.html', 'Cr%C3%A8me_de_violette.html', 'Crab-eating_frog.html', 'Craig_Chester.html', 'Crawley_Down.html', 'Crazy_(2000_film).html', 'Crazy_House_(1928_film).html', 'Crepidula_atrasolea.html', 'Cricoid_pressure.html', 'Criminal_Code_(Canada).html', 'Crisfield_Municipal_Airport.html', 'Crispoldus.html', 'Criss_Cross_(film).html', 'Cristian_Berdeja.html', 'Cryptographic_primitive.html', 'Ctenodes_zonata.html', 'Cultural_tourism_in_Egypt.html', 'Cuproxena_hoffmanana.html', 'Curridge.html', 'Curtis_F._Marbut.html', 'Curtis_Jones_(law).html', 'Curtis_Whitley.html', 'Curtiss-Wright_Hangar_(Columbia,_South_Carolina).html', 'Cyclohexane_conformation.html', 'Cyclone_Gamede.html', 'Cygany,_Masovian_Voivodeship.html', 'Dabir_Khan.html', 'Dachuan_District.html', 'Dahan-e_Kanak.html', 'Dailyhunt.html', 'Dakar_2:_The_World%27s_Ultimate_Rally.html', 'Dalian_Road_Station.html', 'Danbury_Ridge_Nature_Reserves.html', 'Dance_notation.html', 'Dancing_with_the_Stars_(Greece_season_5).html', 'Dani%C3%ABl_de_Clercq.html', 'Daniel_Cerone.html', 'Daniel_Glazman.html', 'Daniela_Del_Din.html', 'Daniella_Abreu.html', 'Danish_Maritime_Safety_Administration.html', 'Danny_Gray.html', 'Darantasia_cuneiplena.html', 'Daryl_Stanley.html', 'DataMeet.html', 'Datang,_Zhuji.html', 'Dave_Hill_(golfer).html', 'David_Beasley.html', 'David_Jesson.html', 'David_Mandel.html', 'David_Sands_(psychologist).html', 'David_Sencer.html', 'David_Solomona.html', 'David_Thomson,_3rd_Baron_Thomson_of_Fleet.html', 'Days_Creek_Formation.html', 'De_Bruijn_index.html', 'De_La_Salle_University_%E2%80%93_Dasmari%C3%B1as.html', 'Dean_Downing.html', 'Dean_Kukan.html', 'Deception_(Irish_TV_series).html', 'Decker_Township,_Richland_County,_Illinois.html', 'Decoy_receptors.html', 'Degerfors_IF.html', 'Delta_Wedding.html', 'Delvenau.html', 'Democratic_Forum_of_Germans_in_Romania.html', 'Demographics_of_American_Samoa.html', 'Demographics_of_Wallis_and_Futuna.html', 'Denis_Augustine_Hanley.html', 'Dennis_Chapman.html', 'Dennis_Shere.html', 'Denyse_Sibley.html', 'Der_Opernball.html', 'Derek_Acorah.html', 'Dermatomycosis.html', 'Derrick_White_(baseball).html', 'Desert_Rain_(song).html', 'Deserticossus_murinus.html', 'Desmiphora_bijuba.html', 'Destroyer_Squadron_7.html', 'Deuterocohnia_schreiteri.html', 'Devarampally.html', 'Developmental_robotics.html', 'Devil_on_Horseback.html', 'Devitt_Insurance.html', 'Devizes_Town_F.C..html', 'Dewoitine_D.21.html', 'Dextran_1.html', 'Dhanbad_(Vidhan_Sabha_constituency).html', 'Diablo_Swing_Orchestra.html', 'Dialogue_for_Hungary.html', 'Dick_Johnson_(clarinetist).html', 'Dick_Persson.html', 'Diego_Galv%C3%A1n.html', 'DiGiorgio_Corporation.html', 'Digital_Light_Processing.html', 'Dik%C4%BCi_parish.html', 'Dimanche_%C3%A0_Bamako.html', 'Dimension_of_an_algebraic_variety.html', 'Diphilus_(physician).html', 'Diplacus_aurantiacus.html', 'Discretionary_trust.html', 'Distance_Education_Centre,_Victoria.html', 'Divine_Incantations_Scripture.html', 'DJ-Kicks:_Henrik_Schwarz.html', 'Dmytrivka,_Shakhtarsk_Raion.html', 'Dokri_Taluka.html', 'Domaniowice.html', 'Domenico_Siniscalco.html', 'Dominique_Voynet.html', 'Don_Kindt,_Jr..html', 'Don_Nelson_Laramore.html', 'Don_Parsons_(ice_hockey).html', 'Don_Raye.html', 'Donal_Moloney.html', 'Donegal_Township,_Westmoreland_County,_Pennsylvania.html', 'Double_Wing_Attack.html', 'Doug_Sahm_and_Band.html', 'Doughty.html', 'Douglas_Trojans.html', 'Doumanaba.html', 'Dowell_Philip_O%27Reilly.html', 'Downhill_Domination.html', 'Dr._Feelgood_(album).html', 'Dragnet_(franchise).html', 'Dresden-Plauen_railway_station.html', 'Drumstruck.html', 'Dryas_integrifolia.html', 'Du%C5%A1anovo.html', 'Du%C5%BEi_Monastery.html', 'Durham_Women%27s_F.C..html', 'DWTE-TV.html', 'DXRA.html', 'Dysgonia_pudica.html', 'Dzahadjou_Lamzand%C3%A9.html', 'DZYM.html', 'E._E._Evans-Pritchard.html', 'E._F._McClellan.html', 'Earl_of_Anglesey.html', 'Early_medieval_states_in_Kazakhstan.html', 'Earth_Liberation_Front.html', 'EarthCheck_Assessed.html', 'East_Bloomfield_Historic_District.html', 'East_Down_(Northern_Ireland_Parliament_constituency).html', 'Eastbrook_Academy.html', 'Eastern_Finnmark_Police_District.html', 'Echembrotus.html', 'Eco-Drive.html', 'Ed_Jackson_(rugby_player).html', 'Eddie_Durie.html', 'Eddie_Eyre.html', 'Edmonton_municipal_election,_1961.html', 'EDP_Sarichioi_Wind_Farm.html', 'Eduardo_De_Filippo.html', 'Education_and_Training_Board.html', 'Education_in_Tacloban.html', 'Edward_Grosvenor.html', 'Edward_Holmes_Baldock_(dealer).html', 'Edwin_Bollier.html', 'Egg_coffee.html', 'Eggerberg_railway_station.html', 'Ego_Dominus_Tuus.html', 'Einstein_(horse).html', 'Eivind_Hiis_Hauge.html', 'Ek_Dil_Sau_Afsane.html', 'El%C5%BCbieta_Dru%C5%BCbacka.html', 'El_Bordj.html', 'El_Pas_de_la_Casa.html', 'Elaine_Fleming.html', 'ELED.html', 'Elgin_National_Watch_Company.html', 'Elio_Calderini.html', 'Elisa_von_der_Recke.html', 'Elizabeth_Gray_(fossil_collector).html', 'Elo%C3%ADna_Miyares_Berm%C3%BAdez.html', 'Els_Dottermans.html', 'Elzear_Torreggiani.html', 'Emarginula_koon.html', 'Embraer_Unidade_Gavi%C3%A3o_Peixoto_Airport.html', 'EMD_SD40-2.html', 'Emily_(1964_song).html', 'Eminencia.html', 'Emmanuel_Muhammad.html', 'Emperor_(novel_series).html', 'Enamul_Haque_(cricketer,_born_1966).html', 'Endre_Church.html', 'ENESSERE.html', 'English_cricket_team_in_South_Africa_in_1956%E2%80%9357.html', 'ENMAX_Centrium.html', 'Enrique_Morales.html', 'Environmental_impact_of_agriculture.html', 'Epichorista.html', 'Epropetes_metallica.html', 'Equestrian_at_the_1936_Summer_Olympics.html', 'Erd%C5%91s%E2%80%93Faber%E2%80%93Lov%C3%A1sz_conjecture.html', 'Eressa_aperiens.html', 'Eric_Ziebold.html', 'Erigeron_canaani.html', 'Erwin_Lutzer.html', 'Eryngium_planum.html', 'Esher_Church_of_England_High_School.html', 'Estadio_Municipal_Pozoblanco.html', 'Estelle_v._Smith.html', 'Eternamente_Romanticos.html', 'Ethan_Van_der_Ryn.html', 'Ethel_Johns.html', 'ETS-VIII.html', 'Eudonia_notozeucta.html', 'Eugamandus_brunneus.html', 'Eugenio_Morelli.html', 'Eupithecia_trancasae.html', 'Europa_(Roman_province).html', 'Euxoa_simulata.html', 'Evanston,_Cincinnati.html', 'Evene.html', 'Ewa_Kasprzyk_(athlete).html', 'Explanation_module.html', 'Exploratorium_(film).html', 'Extension_of_the_Wish.html', 'Eye_of_the_Beholder_III:_Assault_on_Myth_Drannor.html', 'Eyes_Galaxies.html', 'F%C3%A9lix_C%C3%A1rdenas.html', 'F._L._Griggs.html', 'Faat_Zakirov.html', 'Face_Drop.html', 'Faces_(Run%E2%80%93D.M.C._song).html', 'Facial_cleft.html', 'Facundo_Gamband%C3%A9.html', 'Fahy,_County_Mayo.html', 'Failing_Office_Building.html', 'Faizullah.html', 'Falman-County_Acres,_Texas.html', 'False_pregnancy.html', 'Faryab,_Dashtestan.html', 'FC_Bobruisk.html', 'FC_Khikhani_Khulo.html', 'Fe%27i_banana.html', 'Fear_play.html', 'Feel_No_Fret.html', 'Feiner_v._New_York.html', 'Feodosia_Morozova.html', 'Ferdinand_Arnodin.html', 'Ferdinand_Mainzer.html', 'Feria_del_Sol_(M%C3%A9rida).html', 'Fernanda_Vasconcellos.html', 'Feuerzangenbowle.html', 'Fictionwise.html', 'Fifty_Years_of_Music.html', 'Filip_Pyrochta.html', 'Filochy.html', 'Findwell.html', 'FinnSec_Security.html', 'Finnveden.html', 'Firebaugh,_California.html', 'Fireworks_EP.html', 'Firmin%C3%B3polis.html', 'Fischli.html', 'Flag_of_Chicago.html', 'Flag_of_the_Austral_Islands.html', 'Flashmob_(album).html', 'Flat_roof.html', 'Fleetwood,_Oklahoma.html', 'Flight_Design_Boxtair.html', 'Flour_Babies.html', 'Foidolite.html', 'Foilbacks.html', 'Follow_(album).html', 'Football_at_the_National_Games_of_China.html', 'Football_Foundation.html', 'Fort_Astoria.html', 'Fortabat_Art_Collection.html', 'Forth_and_Bargy_dialect.html', 'Fortuna_Glacier.html', 'Forward_Operating_Base_Grizzly.html', 'Fougangoue.html', 'Foulonia.html', 'Fractured_(Everything_I_Said_Was_True).html', 'France_in_the_Eurovision_Song_Contest_2010.html', 'Frances_Morris_(actress).html', 'Frank_C._Archibald_(Vermont_politician).html', 'Frank_Drum.html', 'Frank_Gross.html', 'Frans,_Ain.html', 'Franz_Georg_Benkert.html', 'Fraser_Lake_Airport.html', 'Fred_H._Hildebrandt.html', 'Fred_Marks.html', 'Frederick_Leadbetter.html', 'Freedom_(White_Heart_album).html', 'Freehold_Township_Schools.html', 'Friedrich_Albrecht_Anton_Meyer.html', 'Friedrich_Kirchner.html', 'Friendship,_Wake_County,_North_Carolina.html', 'Frisilia_sulcata.html', 'Frithjof_Schmidt.html', 'From_All_Sides.html', 'Frost_Township,_Michigan.html', 'Fu_Biao.html', 'Fucibet.html', 'Functoid.html', 'Fureai_kippu.html', 'Furkan_Korkmaz.html', 'Furto_di_sera_bel_colpo_si_spera.html', 'Furubira_District,_Hokkaido.html', 'Fusinus_carvalhoriosi.html', 'Future_Weather.html', 'G%C3%B3ra,_Mogilno_County.html', 'G%C3%B6ncruszka.html', 'G.O.Y.A._(Gunz_Or_Yay_Available).html', 'G.S._Lamias_Achilleus.html', 'Ga%C5%A1parci.html', 'Gabriele_Poso.html', 'Gacharageini.html', 'Gad_(deity).html', 'Gaetanus_Matthew_Perez.html', 'Gal%C3%A1pagos,_Guadalajara.html', 'Galician_Nationalist_Bloc.html', 'Galloway_and_Upper_Nithsdale_(Scottish_Parliament_constituency).html', 'Gander_(surname).html', 'Gandigwad.html', 'Gang_run_printing.html', 'Garde_Civique.html', 'Garden-based_learning.html', ...]
In [3]:
len(os.listdir("wiki"))
Out[3]:
2997
In [4]:
with open("wiki/Cecil_Peak.html") as f:
print(f.read())
<!DOCTYPE html>
<html class="client-nojs" lang="en" dir="ltr">
<head>
<meta charset="UTF-8"/>
<title>Cecil Peak - Wikipedia</title>
<script>document.documentElement.className = document.documentElement.className.replace( /(^|\s)client-nojs(\s|$)/, "$1client-js$2" );</script>
<script>(window.RLQ=window.RLQ||[]).push(function(){mw.config.set({"wgCanonicalNamespace":"","wgCanonicalSpecialPageName":false,"wgNamespaceNumber":0,"wgPageName":"Cecil_Peak","wgTitle":"Cecil Peak","wgCurRevisionId":724716112,"wgRevisionId":724716112,"wgArticleId":36574331,"wgIsArticle":true,"wgIsRedirect":false,"wgAction":"view","wgUserName":null,"wgUserGroups":["*"],"wgCategories":["Coordinates on Wikidata","All stub articles","Mountains of Otago","Queenstown-Lakes District","Southern Alps","Otago geography stubs"],"wgBreakFrames":false,"wgPageContentLanguage":"en","wgPageContentModel":"wikitext","wgSeparatorTransformTable":["",""],"wgDigitTransformTable":["",""],"wgDefaultDateFormat":"dmy","wgMonthNames":["","January","February","March","April","May","June","July","August","September","October","November","December"],"wgMonthNamesShort":["","Jan","Feb","Mar","Apr","May","Jun","Jul","Aug","Sep","Oct","Nov","Dec"],"wgRelevantPageName":"Cecil_Peak","wgRelevantArticleId":36574331,"wgRequestId":"WLhgJApAADkAAI@nTZ4AAACB","wgIsProbablyEditable":true,"wgRestrictionEdit":[],"wgRestrictionMove":[],"wgFlaggedRevsParams":{"tags":{}},"wgStableRevisionId":null,"wgWikiEditorEnabledModules":{"toolbar":true,"dialogs":true,"preview":false,"publish":false},"wgBetaFeaturesFeatures":[],"wgMediaViewerOnClick":true,"wgMediaViewerEnabledByDefault":true,"wgPopupsShouldSendModuleToUser":false,"wgPopupsConflictsWithNavPopupGadget":false,"wgVisualEditor":{"pageLanguageCode":"en","pageLanguageDir":"ltr","usePageImages":true,"usePageDescriptions":true},"wgPreferredVariant":"en","wgMFDisplayWikibaseDescriptions":{"search":true,"nearby":true,"watchlist":true,"tagline":true},"wgRelatedArticles":null,"wgRelatedArticlesBetaFeatureEnabled":false,"wgRelatedArticlesUseCirrusSearch":true,"wgRelatedArticlesOnlyUseCirrusSearch":false,"wgULSCurrentAutonym":"English","wgNoticeProject":"wikipedia","wgCentralNoticeCookiesToDelete":[],"wgCentralNoticeCategoriesUsingLegacy":["Fundraising","fundraising"],"wgCategoryTreePageCategoryOptions":"{\"mode\":0,\"hideprefix\":20,\"showcount\":true,\"namespaces\":false}","wgCoordinates":{"lat":-45.108831,"lon":168.628463},"wgWikibaseItemId":"Q5056265","wgCentralAuthMobileDomain":false,"wgVisualEditorToolbarScrollOffset":0,"wgEditSubmitButtonLabelPublish":false});mw.loader.state({"ext.globalCssJs.user.styles":"ready","ext.globalCssJs.site.styles":"ready","site.styles":"ready","noscript":"ready","user.styles":"ready","user":"ready","user.options":"loading","user.tokens":"loading","ext.cite.styles":"ready","wikibase.client.init":"ready","ext.visualEditor.desktopArticleTarget.noscript":"ready","ext.uls.interlanguage":"ready","ext.wikimediaBadges":"ready","mediawiki.legacy.shared":"ready","mediawiki.legacy.commonPrint":"ready","mediawiki.sectionAnchor":"ready","mediawiki.skinning.interface":"ready","skins.vector.styles":"ready","ext.globalCssJs.user":"ready","ext.globalCssJs.site":"ready"});mw.loader.implement("user.options@0j3lz3q",function($,jQuery,require,module){mw.user.options.set({"variant":"en"});});mw.loader.implement("user.tokens@1dqfd7l",function ( $, jQuery, require, module ) {
mw.user.tokens.set({"editToken":"+\\","patrolToken":"+\\","watchToken":"+\\","csrfToken":"+\\"});/*@nomin*/;
});mw.loader.load(["ext.cite.a11y","mediawiki.action.view.postEdit","site","mediawiki.page.startup","mediawiki.user","mediawiki.hidpi","mediawiki.page.ready","mediawiki.legacy.wikibits","mediawiki.searchSuggest","ext.gadget.teahouse","ext.gadget.ReferenceTooltips","ext.gadget.watchlist-notice","ext.gadget.DRN-wizard","ext.gadget.charinsert","ext.gadget.refToolbar","ext.gadget.extra-toolbar-buttons","ext.gadget.switcher","ext.gadget.featured-articles-links","ext.centralauth.centralautologin","mmv.head","mmv.bootstrap.autostart","ext.visualEditor.desktopArticleTarget.init","ext.visualEditor.targetLoader","ext.eventLogging.subscriber","ext.wikimediaEvents","ext.navigationTiming","ext.uls.eventlogger","ext.uls.init","ext.uls.interface","ext.quicksurveys.init","ext.centralNotice.geoIP","ext.centralNotice.startUp","skins.vector.js"]);});</script>
<link rel="stylesheet" href="/w/load.php?debug=false&lang=en&modules=ext.cite.styles%7Cext.uls.interlanguage%7Cext.visualEditor.desktopArticleTarget.noscript%7Cext.wikimediaBadges%7Cmediawiki.legacy.commonPrint%2Cshared%7Cmediawiki.sectionAnchor%7Cmediawiki.skinning.interface%7Cskins.vector.styles%7Cwikibase.client.init&only=styles&skin=vector"/>
<script async="" src="/w/load.php?debug=false&lang=en&modules=startup&only=scripts&skin=vector"></script>
<meta name="ResourceLoaderDynamicStyles" content=""/>
<link rel="stylesheet" href="/w/load.php?debug=false&lang=en&modules=site.styles&only=styles&skin=vector"/>
<meta name="generator" content="MediaWiki 1.29.0-wmf.13"/>
<meta name="referrer" content="origin-when-cross-origin"/>
<link rel="alternate" href="android-app://org.wikipedia/http/en.m.wikipedia.org/wiki/Cecil_Peak"/>
<link rel="alternate" type="application/x-wiki" title="Edit this page" href="/w/index.php?title=Cecil_Peak&action=edit"/>
<link rel="edit" title="Edit this page" href="/w/index.php?title=Cecil_Peak&action=edit"/>
<link rel="apple-touch-icon" href="/static/apple-touch/wikipedia.png"/>
<link rel="shortcut icon" href="/static/favicon/wikipedia.ico"/>
<link rel="search" type="application/opensearchdescription+xml" href="/w/opensearch_desc.php" title="Wikipedia (en)"/>
<link rel="EditURI" type="application/rsd+xml" href="//en.wikipedia.org/w/api.php?action=rsd"/>
<link rel="copyright" href="//creativecommons.org/licenses/by-sa/3.0/"/>
<link rel="canonical" href="https://en.wikipedia.org/wiki/Cecil_Peak"/>
<link rel="dns-prefetch" href="//login.wikimedia.org"/>
<link rel="dns-prefetch" href="//meta.wikimedia.org" />
</head>
<body class="mediawiki ltr sitedir-ltr mw-hide-empty-elt ns-0 ns-subject page-Cecil_Peak rootpage-Cecil_Peak skin-vector action-view"> <div id="mw-page-base" class="noprint"></div>
<div id="mw-head-base" class="noprint"></div>
<div id="content" class="mw-body" role="main">
<a id="top"></a>
<div id="siteNotice"><!-- CentralNotice --></div>
<div class="mw-indicators">
</div>
<h1 id="firstHeading" class="firstHeading" lang="en">Cecil Peak</h1>
<div id="bodyContent" class="mw-body-content">
<div id="siteSub">From Wikipedia, the free encyclopedia</div>
<div id="contentSub"></div>
<div id="jump-to-nav" class="mw-jump">
Jump to: <a href="#mw-head">navigation</a>, <a href="#p-search">search</a>
</div>
<div id="mw-content-text" lang="en" dir="ltr" class="mw-content-ltr"><p><b>Cecil Peak</b> is a mountain in the <a href="/wiki/Wakatipu_Basin" title="Wakatipu Basin">Wakatipu Basin</a>, <a href="/wiki/New_Zealand" title="New Zealand">New Zealand</a> and reaches a height of 1,978 metres.<sup id="cite_ref-1" class="reference"><a href="#cite_note-1">[1]</a></sup> It is on the south side of <a href="/wiki/Lake_Wakatipu" title="Lake Wakatipu">Lake Wakatipu</a>, south south-west of <a href="/wiki/Queenstown,_New_Zealand" title="Queenstown, New Zealand">Queenstown</a> and is highly prominent from around this area. <sup id="cite_ref-2" class="reference"><a href="#cite_note-2">[2]</a></sup></p>
<div class="thumb tright">
<div class="thumbinner" style="width:502px;"><a href="/wiki/File:Cecil-Peak-and-Walter-Peak-with-snow.jpg" class="image"><img alt="" src="//upload.wikimedia.org/wikipedia/commons/thumb/9/97/Cecil-Peak-and-Walter-Peak-with-snow.jpg/500px-Cecil-Peak-and-Walter-Peak-with-snow.jpg" width="500" height="158" class="thumbimage" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/9/97/Cecil-Peak-and-Walter-Peak-with-snow.jpg/750px-Cecil-Peak-and-Walter-Peak-with-snow.jpg 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/9/97/Cecil-Peak-and-Walter-Peak-with-snow.jpg/1000px-Cecil-Peak-and-Walter-Peak-with-snow.jpg 2x" data-file-width="3608" data-file-height="1143" /></a>
<div class="thumbcaption">
<div class="magnify"><a href="/wiki/File:Cecil-Peak-and-Walter-Peak-with-snow.jpg" class="internal" title="Enlarge"></a></div>
View from Fernhill of Cecil Peak (<a href="/wiki/Walter_Peak,_New_Zealand" class="mw-redirect" title="Walter Peak, New Zealand">Walter Peak</a> on right). Kā Kamu-a-Hakitekura is the <a href="/wiki/M%C4%81ori_language" title="Māori language">Māori</a> name for both mountains.</div>
</div>
</div>
<p>Vegetation is mainly grass and tussock (as it is under a pastoral lease<sup id="cite_ref-3" class="reference"><a href="#cite_note-3">[3]</a></sup>) with trees near the waterline. <a href="/wiki/Hidden_Island,_New_Zealand" class="mw-redirect" title="Hidden Island, New Zealand">Hidden Island</a> is one of four islands in Lake Wakatipu and sits very close to the shoreline of Cecil Peak. On 27 March 2010 a local band performed an outdoor concert in a natural amphitheatre on the peak playing songs from the band <a href="/wiki/Pink_Floyd" title="Pink Floyd">Pink Floyd</a>.<sup id="cite_ref-4" class="reference"><a href="#cite_note-4">[4]</a></sup></p>
<h2><span class="mw-headline" id="Name">Name</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Cecil_Peak&action=edit&section=1" title="Edit section: Name">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
<p>Both Cecil Peak and the nearby mountain of Walter Peak were named after <a href="/wiki/William_Gilbert_Rees" title="William Gilbert Rees">William Rees'</a> eldest sons' first given names by the surveyor <a href="/wiki/James_McKerrow" title="James McKerrow">James McKerrow</a> in 1862.<sup id="cite_ref-5" class="reference"><a href="#cite_note-5">[5]</a></sup></p>
<h2><span class="mw-headline" id="See_also">See also</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Cecil_Peak&action=edit&section=2" title="Edit section: See also">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
<ul>
<li><a href="/wiki/List_of_mountains_of_New_Zealand_by_height" title="List of mountains of New Zealand by height">List of mountains of New Zealand by height</a></li>
<li><a href="/wiki/Walter_Peak_(New_Zealand)" title="Walter Peak (New Zealand)">Walter Peak</a></li>
</ul>
<h2><span class="mw-headline" id="References">References</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Cecil_Peak&action=edit&section=3" title="Edit section: References">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
<div class="reflist" style="list-style-type: decimal;">
<ol class="references">
<li id="cite_note-1"><span class="mw-cite-backlink"><b><a href="#cite_ref-1">^</a></b></span> <span class="reference-text"><cite class="citation web">Malcolm, McKinnon. <a rel="nofollow" class="external text" href="http://www.teara.govt.nz/en/otago-places/17">"Otago places - Wakatipu basin"</a>. Te Ara - the Encyclopedia of New Zealand.</cite><span title="ctx_ver=Z39.88-2004&rfr_id=info%3Asid%2Fen.wikipedia.org%3ACecil+Peak&rft.aufirst=McKinnon&rft.aulast=Malcolm&rft.btitle=Otago+places+-+Wakatipu+basin&rft.genre=unknown&rft_id=http%3A%2F%2Fwww.teara.govt.nz%2Fen%2Fotago-places%2F17&rft.pub=Te+Ara+-+the+Encyclopedia+of+New+Zealand&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook" class="Z3988"><span style="display:none;"> </span></span></span></li>
<li id="cite_note-2"><span class="mw-cite-backlink"><b><a href="#cite_ref-2">^</a></b></span> <span class="reference-text"><cite class="citation web"><a rel="nofollow" class="external text" href="http://www.tekaraka.co.nz/Issues/TeKaraka44.pdf">"Ngai Tahu Names"</a> <span style="font-size:85%;">(PDF)</span>. <i>Te Karaka Issue 44, pg 13</i>. tekaraka.co.nz<span class="reference-accessdate">. Retrieved <span class="nowrap">18 September</span> 2013</span>.</cite><span title="ctx_ver=Z39.88-2004&rfr_id=info%3Asid%2Fen.wikipedia.org%3ACecil+Peak&rft.atitle=Ngai+Tahu+Names&rft.genre=unknown&rft_id=http%3A%2F%2Fwww.tekaraka.co.nz%2FIssues%2FTeKaraka44.pdf&rft.jtitle=Te+Karaka+Issue+44%2C+pg+13&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal" class="Z3988"><span style="display:none;"> </span></span></span></li>
<li id="cite_note-3"><span class="mw-cite-backlink"><b><a href="#cite_ref-3">^</a></b></span> <span class="reference-text"><cite class="citation web"><a rel="nofollow" class="external text" href="http://www.linz.govt.nz/sites/default/files/docs/crownproperty/high-country-leases/leaselist/cecil-peak-ddr-pt1.pdf">"Crown Pastoral Land Tenure Review"</a> <span style="font-size:85%;">(PDF)</span>. Land Information New Zealand.</cite><span title="ctx_ver=Z39.88-2004&rfr_id=info%3Asid%2Fen.wikipedia.org%3ACecil+Peak&rft.btitle=Crown+Pastoral+Land+Tenure+Review&rft.genre=unknown&rft_id=http%3A%2F%2Fwww.linz.govt.nz%2Fsites%2Fdefault%2Ffiles%2Fdocs%2Fcrownproperty%2Fhigh-country-leases%2Fleaselist%2Fcecil-peak-ddr-pt1.pdf&rft.pub=Land+Information+New+Zealand&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook" class="Z3988"><span style="display:none;"> </span></span></span></li>
<li id="cite_note-4"><span class="mw-cite-backlink"><b><a href="#cite_ref-4">^</a></b></span> <span class="reference-text"><cite class="citation web"><a rel="nofollow" class="external text" href="http://www.scoop.co.nz/stories/CU1003/S00353.htm">"Rocking it on Cecil Peak"</a>. Scoop Media.</cite><span title="ctx_ver=Z39.88-2004&rfr_id=info%3Asid%2Fen.wikipedia.org%3ACecil+Peak&rft.btitle=Rocking+it+on+Cecil+Peak&rft.genre=unknown&rft_id=http%3A%2F%2Fwww.scoop.co.nz%2Fstories%2FCU1003%2FS00353.htm&rft.pub=Scoop+Media&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook" class="Z3988"><span style="display:none;"> </span></span></span></li>
<li id="cite_note-5"><span class="mw-cite-backlink"><b><a href="#cite_ref-5">^</a></b></span> <span class="reference-text"><cite class="citation book">Jardine, D.G. (1978). <i>Shadows on the Hill</i>. A.H. & A.W. Reed Ltd. p. 185. <a href="/wiki/International_Standard_Book_Number" title="International Standard Book Number">ISBN</a> <a href="/wiki/Special:BookSources/0589010093" title="Special:BookSources/0589010093">0589010093</a>.</cite><span title="ctx_ver=Z39.88-2004&rfr_id=info%3Asid%2Fen.wikipedia.org%3ACecil+Peak&rft.aufirst=D.G.&rft.aulast=Jardine&rft.btitle=Shadows+on+the+Hill&rft.date=1978&rft.genre=book&rft.isbn=0589010093&rft.pages=185&rft.pub=A.H.+%26+A.W.+Reed+Ltd&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook" class="Z3988"><span style="display:none;"> </span></span></span></li>
</ol>
</div>
<p><span style="font-size: small;"><span id="coordinates"><a href="/wiki/Geographic_coordinate_system" title="Geographic coordinate system">Coordinates</a>: <span class="plainlinks nourlexpansion"><a class="external text" href="//tools.wmflabs.org/geohack/geohack.php?pagename=Cecil_Peak&params=-45.108831_N_168.628463_E_"><span class="geo-nondefault"><span class="geo-dms" title="Maps, aerial photos, and other data for this location"><span class="latitude">45°06′32″S</span> <span class="longitude">168°37′42″E</span></span></span><span class="geo-multi-punct"> / </span><span class="geo-default"><span class="geo-dec" title="Maps, aerial photos, and other data for this location">45.108831°S 168.628463°E</span><span style="display:none"> / <span class="geo">-45.108831; 168.628463</span></span></span></a></span></span></span></p>
<p><br /></p>
<table class="metadata plainlinks stub" role="presentation" style="background:transparent">
<tr>
<td><a href="/wiki/File:Position_of_Otago.png" class="image"><img alt="Stub icon" src="//upload.wikimedia.org/wikipedia/commons/thumb/e/ee/Position_of_Otago.png/32px-Position_of_Otago.png" width="32" height="47" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/e/ee/Position_of_Otago.png/48px-Position_of_Otago.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/e/ee/Position_of_Otago.png/64px-Position_of_Otago.png 2x" data-file-width="405" data-file-height="590" /></a></td>
<td><i>This <a href="/wiki/Otago" title="Otago">Otago</a> geography article is a <a href="/wiki/Wikipedia:Stub" title="Wikipedia:Stub">stub</a>. You can help Wikipedia by <a class="external text" href="//en.wikipedia.org/w/index.php?title=Cecil_Peak&action=edit">expanding it</a>.</i>
<div class="plainlinks hlist navbar mini" style="position: absolute; right: 15px; display: none;">
<ul>
<li class="nv-view"><a href="/wiki/Template:Otago-geo-stub" title="Template:Otago-geo-stub"><abbr title="View this template">v</abbr></a></li>
<li class="nv-talk"><a href="/wiki/Template_talk:Otago-geo-stub" title="Template talk:Otago-geo-stub"><abbr title="Discuss this template">t</abbr></a></li>
<li class="nv-edit"><a class="external text" href="//en.wikipedia.org/w/index.php?title=Template:Otago-geo-stub&action=edit"><abbr title="Edit this template">e</abbr></a></li>
</ul>
</div>
</td>
</tr>
</table>
<!--
NewPP limit report
Parsed by mw1211
Cached time: 20170210085052
Cache expiry: 2592000
Dynamic content: false
CPU time usage: 0.080 seconds
Real time usage: 0.107 seconds
Preprocessor visited node count: 253/1000000
Preprocessor generated node count: 0/1500000
Post‐expand include size: 10233/2097152 bytes
Template argument size: 0/2097152 bytes
Highest expansion depth: 4/40
Expensive parser function count: 0/500
Lua time usage: 0.043/10.000 seconds
Lua memory usage: 2.57 MB/50 MB
-->
<!--
Transclusion expansion time report (%,ms,calls,template)
100.00% 89.189 1 -total
62.17% 55.447 1 Template:Reflist
48.96% 43.664 4 Template:Cite_web
24.91% 22.219 1 Template:Coord
12.74% 11.365 1 Template:Otago-geo-stub
11.34% 10.113 1 Template:Asbox
4.71% 4.200 1 Template:Cite_book
-->
<!-- Saved in parser cache with key enwiki:pcache:idhash:36574331-0!*!0!!*!4!* and timestamp 20170210085052 and revision id 724716112
-->
<noscript><img src="//en.wikipedia.org/wiki/Special:CentralAutoLogin/start?type=1x1" alt="" title="" width="1" height="1" style="border: none; position: absolute;" /></noscript></div> <div class="printfooter">
Retrieved from "<a dir="ltr" href="https://en.wikipedia.org/w/index.php?title=Cecil_Peak&oldid=724716112">https://en.wikipedia.org/w/index.php?title=Cecil_Peak&oldid=724716112</a>" </div>
<div id="catlinks" class="catlinks" data-mw="interface"><div id="mw-normal-catlinks" class="mw-normal-catlinks"><a href="/wiki/Help:Category" title="Help:Category">Categories</a>: <ul><li><a href="/wiki/Category:Mountains_of_Otago" title="Category:Mountains of Otago">Mountains of Otago</a></li><li><a href="/wiki/Category:Queenstown-Lakes_District" title="Category:Queenstown-Lakes District">Queenstown-Lakes District</a></li><li><a href="/wiki/Category:Southern_Alps" title="Category:Southern Alps">Southern Alps</a></li><li><a href="/wiki/Category:Otago_geography_stubs" title="Category:Otago geography stubs">Otago geography stubs</a></li></ul></div><div id="mw-hidden-catlinks" class="mw-hidden-catlinks mw-hidden-cats-hidden">Hidden categories: <ul><li><a href="/wiki/Category:Coordinates_on_Wikidata" title="Category:Coordinates on Wikidata">Coordinates on Wikidata</a></li><li><a href="/wiki/Category:All_stub_articles" title="Category:All stub articles">All stub articles</a></li></ul></div></div> <div class="visualClear"></div>
</div>
</div>
<div id="mw-navigation">
<h2>Navigation menu</h2>
<div id="mw-head">
<div id="p-personal" role="navigation" class="" aria-labelledby="p-personal-label">
<h3 id="p-personal-label">Personal tools</h3>
<ul>
<li id="pt-anonuserpage">Not logged in</li><li id="pt-anontalk"><a href="/wiki/Special:MyTalk" title="Discussion about edits from this IP address [n]" accesskey="n">Talk</a></li><li id="pt-anoncontribs"><a href="/wiki/Special:MyContributions" title="A list of edits made from this IP address [y]" accesskey="y">Contributions</a></li><li id="pt-createaccount"><a href="/w/index.php?title=Special:CreateAccount&returnto=Cecil+Peak" title="You are encouraged to create an account and log in; however, it is not mandatory">Create account</a></li><li id="pt-login"><a href="/w/index.php?title=Special:UserLogin&returnto=Cecil+Peak" title="You're encouraged to log in; however, it's not mandatory. [o]" accesskey="o">Log in</a></li> </ul>
</div>
<div id="left-navigation">
<div id="p-namespaces" role="navigation" class="vectorTabs" aria-labelledby="p-namespaces-label">
<h3 id="p-namespaces-label">Namespaces</h3>
<ul>
<li id="ca-nstab-main" class="selected"><span><a href="/wiki/Cecil_Peak" title="View the content page [c]" accesskey="c">Article</a></span></li>
<li id="ca-talk"><span><a href="/wiki/Talk:Cecil_Peak" title="Discussion about the content page [t]" accesskey="t" rel="discussion">Talk</a></span></li>
</ul>
</div>
<div id="p-variants" role="navigation" class="vectorMenu emptyPortlet" aria-labelledby="p-variants-label">
<h3 id="p-variants-label">
<span>Variants</span><a href="#"></a>
</h3>
<div class="menu">
<ul>
</ul>
</div>
</div>
</div>
<div id="right-navigation">
<div id="p-views" role="navigation" class="vectorTabs" aria-labelledby="p-views-label">
<h3 id="p-views-label">Views</h3>
<ul>
<li id="ca-view" class="selected"><span><a href="/wiki/Cecil_Peak" >Read</a></span></li>
<li id="ca-edit"><span><a href="/w/index.php?title=Cecil_Peak&action=edit" title="Edit this page [e]" accesskey="e">Edit</a></span></li>
<li id="ca-history" class="collapsible"><span><a href="/w/index.php?title=Cecil_Peak&action=history" title="Past revisions of this page [h]" accesskey="h">View history</a></span></li>
</ul>
</div>
<div id="p-cactions" role="navigation" class="vectorMenu emptyPortlet" aria-labelledby="p-cactions-label">
<h3 id="p-cactions-label"><span>More</span><a href="#"></a></h3>
<div class="menu">
<ul>
</ul>
</div>
</div>
<div id="p-search" role="search">
<h3>
<label for="searchInput">Search</label>
</h3>
<form action="/w/index.php" id="searchform">
<div id="simpleSearch">
<input type="search" name="search" placeholder="Search Wikipedia" title="Search Wikipedia [f]" accesskey="f" id="searchInput"/><input type="hidden" value="Special:Search" name="title"/><input type="submit" name="fulltext" value="Search" title="Search Wikipedia for this text" id="mw-searchButton" class="searchButton mw-fallbackSearchButton"/><input type="submit" name="go" value="Go" title="Go to a page with this exact name if it exists" id="searchButton" class="searchButton"/> </div>
</form>
</div>
</div>
</div>
<div id="mw-panel">
<div id="p-logo" role="banner"><a class="mw-wiki-logo" href="/wiki/Main_Page" title="Visit the main page"></a></div>
<div class="portal" role="navigation" id='p-navigation' aria-labelledby='p-navigation-label'>
<h3 id='p-navigation-label'>Navigation</h3>
<div class="body">
<ul>
<li id="n-mainpage-description"><a href="/wiki/Main_Page" title="Visit the main page [z]" accesskey="z">Main page</a></li><li id="n-contents"><a href="/wiki/Portal:Contents" title="Guides to browsing Wikipedia">Contents</a></li><li id="n-featuredcontent"><a href="/wiki/Portal:Featured_content" title="Featured content – the best of Wikipedia">Featured content</a></li><li id="n-currentevents"><a href="/wiki/Portal:Current_events" title="Find background information on current events">Current events</a></li><li id="n-randompage"><a href="/wiki/Special:Random" title="Load a random article [x]" accesskey="x">Random article</a></li><li id="n-sitesupport"><a href="https://donate.wikimedia.org/wiki/Special:FundraiserRedirector?utm_source=donate&utm_medium=sidebar&utm_campaign=C13_en.wikipedia.org&uselang=en" title="Support us">Donate to Wikipedia</a></li><li id="n-shoplink"><a href="//shop.wikimedia.org" title="Visit the Wikipedia store">Wikipedia store</a></li> </ul>
</div>
</div>
<div class="portal" role="navigation" id='p-interaction' aria-labelledby='p-interaction-label'>
<h3 id='p-interaction-label'>Interaction</h3>
<div class="body">
<ul>
<li id="n-help"><a href="/wiki/Help:Contents" title="Guidance on how to use and edit Wikipedia">Help</a></li><li id="n-aboutsite"><a href="/wiki/Wikipedia:About" title="Find out about Wikipedia">About Wikipedia</a></li><li id="n-portal"><a href="/wiki/Wikipedia:Community_portal" title="About the project, what you can do, where to find things">Community portal</a></li><li id="n-recentchanges"><a href="/wiki/Special:RecentChanges" title="A list of recent changes in the wiki [r]" accesskey="r">Recent changes</a></li><li id="n-contactpage"><a href="//en.wikipedia.org/wiki/Wikipedia:Contact_us" title="How to contact Wikipedia">Contact page</a></li> </ul>
</div>
</div>
<div class="portal" role="navigation" id='p-tb' aria-labelledby='p-tb-label'>
<h3 id='p-tb-label'>Tools</h3>
<div class="body">
<ul>
<li id="t-whatlinkshere"><a href="/wiki/Special:WhatLinksHere/Cecil_Peak" title="List of all English Wikipedia pages containing links to this page [j]" accesskey="j">What links here</a></li><li id="t-recentchangeslinked"><a href="/wiki/Special:RecentChangesLinked/Cecil_Peak" rel="nofollow" title="Recent changes in pages linked from this page [k]" accesskey="k">Related changes</a></li><li id="t-upload"><a href="/wiki/Wikipedia:File_Upload_Wizard" title="Upload files [u]" accesskey="u">Upload file</a></li><li id="t-specialpages"><a href="/wiki/Special:SpecialPages" title="A list of all special pages [q]" accesskey="q">Special pages</a></li><li id="t-permalink"><a href="/w/index.php?title=Cecil_Peak&oldid=724716112" title="Permanent link to this revision of the page">Permanent link</a></li><li id="t-info"><a href="/w/index.php?title=Cecil_Peak&action=info" title="More information about this page">Page information</a></li><li id="t-wikibase"><a href="https://www.wikidata.org/wiki/Q5056265" title="Link to connected data repository item [g]" accesskey="g">Wikidata item</a></li><li id="t-cite"><a href="/w/index.php?title=Special:CiteThisPage&page=Cecil_Peak&id=724716112" title="Information on how to cite this page">Cite this page</a></li> </ul>
</div>
</div>
<div class="portal" role="navigation" id='p-coll-print_export' aria-labelledby='p-coll-print_export-label'>
<h3 id='p-coll-print_export-label'>Print/export</h3>
<div class="body">
<ul>
<li id="coll-create_a_book"><a href="/w/index.php?title=Special:Book&bookcmd=book_creator&referer=Cecil+Peak">Create a book</a></li><li id="coll-download-as-rdf2latex"><a href="/w/index.php?title=Special:Book&bookcmd=render_article&arttitle=Cecil+Peak&returnto=Cecil+Peak&oldid=724716112&writer=rdf2latex">Download as PDF</a></li><li id="t-print"><a href="/w/index.php?title=Cecil_Peak&printable=yes" title="Printable version of this page [p]" accesskey="p">Printable version</a></li> </ul>
</div>
</div>
<div class="portal" role="navigation" id='p-lang' aria-labelledby='p-lang-label'>
<h3 id='p-lang-label'>Languages</h3>
<div class="body">
<ul>
<li class="interlanguage-link interwiki-ceb"><a href="https://ceb.wikipedia.org/wiki/Cecil_Peak_(tumoy_sa_bukid)" title="Cecil Peak (tumoy sa bukid) – Cebuano" lang="ceb" hreflang="ceb" class="interlanguage-link-target">Cebuano</a></li><li class="interlanguage-link interwiki-cs"><a href="https://cs.wikipedia.org/wiki/Cecil_Peak" title="Cecil Peak – Czech" lang="cs" hreflang="cs" class="interlanguage-link-target">Čeština</a></li><li class="interlanguage-link interwiki-ka"><a href="https://ka.wikipedia.org/wiki/%E1%83%A1%E1%83%94%E1%83%A1%E1%83%98%E1%83%9A%E1%83%98%E1%83%A1_%E1%83%9E%E1%83%98%E1%83%99%E1%83%98" title="სესილის პიკი – Georgian" lang="ka" hreflang="ka" class="interlanguage-link-target">ქართული</a></li><li class="interlanguage-link interwiki-ru"><a href="https://ru.wikipedia.org/wiki/%D0%A1%D0%B5%D1%81%D0%B8%D0%BB-%D0%9F%D0%B8%D0%BA" title="Сесил-Пик – Russian" lang="ru" hreflang="ru" class="interlanguage-link-target">Русский</a></li> </ul>
<div class='after-portlet after-portlet-lang'><span class="wb-langlinks-edit wb-langlinks-link"><a href="https://www.wikidata.org/wiki/Q5056265#sitelinks-wikipedia" title="Edit interlanguage links" class="wbc-editpage">Edit links</a></span></div> </div>
</div>
</div>
</div>
<div id="footer" role="contentinfo">
<ul id="footer-info">
<li id="footer-info-lastmod"> This page was last modified on 11 June 2016, at 01:06.</li>
<li id="footer-info-copyright">Text is available under the <a rel="license" href="//en.wikipedia.org/wiki/Wikipedia:Text_of_Creative_Commons_Attribution-ShareAlike_3.0_Unported_License">Creative Commons Attribution-ShareAlike License</a><a rel="license" href="//creativecommons.org/licenses/by-sa/3.0/" style="display:none;"></a>;
additional terms may apply. By using this site, you agree to the <a href="//wikimediafoundation.org/wiki/Terms_of_Use">Terms of Use</a> and <a href="//wikimediafoundation.org/wiki/Privacy_policy">Privacy Policy</a>. Wikipedia® is a registered trademark of the <a href="//www.wikimediafoundation.org/">Wikimedia Foundation, Inc.</a>, a non-profit organization.</li>
</ul>
<ul id="footer-places">
<li id="footer-places-privacy"><a href="https://wikimediafoundation.org/wiki/Privacy_policy" class="extiw" title="wmf:Privacy policy">Privacy policy</a></li>
<li id="footer-places-about"><a href="/wiki/Wikipedia:About" title="Wikipedia:About">About Wikipedia</a></li>
<li id="footer-places-disclaimer"><a href="/wiki/Wikipedia:General_disclaimer" title="Wikipedia:General disclaimer">Disclaimers</a></li>
<li id="footer-places-contact"><a href="//en.wikipedia.org/wiki/Wikipedia:Contact_us">Contact Wikipedia</a></li>
<li id="footer-places-developers"><a href="https://www.mediawiki.org/wiki/Special:MyLanguage/How_to_contribute">Developers</a></li>
<li id="footer-places-cookiestatement"><a href="https://wikimediafoundation.org/wiki/Cookie_statement">Cookie statement</a></li>
<li id="footer-places-mobileview"><a href="//en.m.wikipedia.org/w/index.php?title=Cecil_Peak&mobileaction=toggle_view_mobile" class="noprint stopMobileRedirectToggle">Mobile view</a></li>
</ul>
<ul id="footer-icons" class="noprint">
<li id="footer-copyrightico">
<a href="https://wikimediafoundation.org/"><img src="/static/images/wikimedia-button.png" srcset="/static/images/wikimedia-button-1.5x.png 1.5x, /static/images/wikimedia-button-2x.png 2x" width="88" height="31" alt="Wikimedia Foundation"/></a> </li>
<li id="footer-poweredbyico">
<a href="//www.mediawiki.org/"><img src="/static/images/poweredby_mediawiki_88x31.png" alt="Powered by MediaWiki" srcset="/static/images/poweredby_mediawiki_132x47.png 1.5x, /static/images/poweredby_mediawiki_176x62.png 2x" width="88" height="31"/></a> </li>
</ul>
<div style="clear:both"></div>
</div>
<script>(window.RLQ=window.RLQ||[]).push(function(){mw.config.set({"wgPageParseReport":{"limitreport":{"cputime":"0.080","walltime":"0.107","ppvisitednodes":{"value":253,"limit":1000000},"ppgeneratednodes":{"value":0,"limit":1500000},"postexpandincludesize":{"value":10233,"limit":2097152},"templateargumentsize":{"value":0,"limit":2097152},"expansiondepth":{"value":4,"limit":40},"expensivefunctioncount":{"value":0,"limit":500},"entityaccesscount":{"value":1,"limit":400},"timingprofile":["100.00% 89.189 1 -total"," 62.17% 55.447 1 Template:Reflist"," 48.96% 43.664 4 Template:Cite_web"," 24.91% 22.219 1 Template:Coord"," 12.74% 11.365 1 Template:Otago-geo-stub"," 11.34% 10.113 1 Template:Asbox"," 4.71% 4.200 1 Template:Cite_book"]},"scribunto":{"limitreport-timeusage":{"value":"0.043","limit":"10.000"},"limitreport-memusage":{"value":2691141,"limit":52428800}},"cachereport":{"origin":"mw1211","timestamp":"20170210085052","ttl":2592000,"transientcontent":false}}});});</script><script>(window.RLQ=window.RLQ||[]).push(function(){mw.config.set({"wgBackendResponseTime":71,"wgHostname":"mw1262"});});</script>
</body>
</html>
It appears that the main content is nested inside the div tag with the id content.
Reading In The Data¶
In [12]:
import concurrent.futures
import time
pool = concurrent.futures.ThreadPoolExecutor(max_workers=4)
def read_data(filename):
with open(filename) as f:
data = f.read()
return data
start = time.time()
filenames = ["wiki/{}".format(f) for f in os.listdir("wiki")]
content = pool.map(read_data, filenames)
content = list(content)
end = time.time()
print(end - start)
articles = [f.replace(".html", "").replace("wiki/", "") for f in filenames]
2.952831983566284
After doing some profiling, it doesn't appear that threading makes a huge difference to performance. It may be because although files are opened, most of the task is offset by the overhead of creating new threads.
Remove Extraneous Markup¶
In [26]:
from bs4 import BeautifulSoup
def parse_html(html):
soup = BeautifulSoup(html, 'html.parser')
return str(soup.find_all("div", id="content")[0])
start = time.time()
pool = concurrent.futures.ProcessPoolExecutor(max_workers=3)
parsed = pool.map(parse_html, content)
parsed = list(parsed)
end = time.time()
print(end - start)
139.67757391929626
In [27]:
parsed[0]
Out[27]:
'<div class="mw-body" id="content" role="main">\n<a id="top"></a>\n<div id="siteNotice"><!-- CentralNotice --></div>\n<div class="mw-indicators">\n</div>\n<h1 class="firstHeading" id="firstHeading" lang="en">Álvaro Sierra</h1>\n<div class="mw-body-content" id="bodyContent">\n<div id="siteSub">From Wikipedia, the free encyclopedia</div>\n<div id="contentSub"></div>\n<div class="mw-jump" id="jump-to-nav">\n\t\t\t\t\tJump to:\t\t\t\t\t<a href="#mw-head">navigation</a>, \t\t\t\t\t<a href="#p-search">search</a>\n</div>\n<div class="mw-content-ltr" dir="ltr" id="mw-content-text" lang="en"><div class="hatnote" role="note">This name uses <a href="/wiki/Spanish_naming_customs" title="Spanish naming customs">Spanish naming customs</a>: the first or paternal <a href="/wiki/Surname" title="Surname">family name</a> is <i>Sierra</i>\xa0and the second or maternal family name is <i>Peña</i>.</div>\n<p><b>Álvaro Sierra Peña</b> (born April 4, 1967 in <a href="/wiki/Sogamoso" title="Sogamoso">Sogamoso</a>, <a href="/wiki/Boyac%C3%A1_Department" title="Boyacá Department">Boyacá</a>) is a retired male professional <a class="mw-redirect" href="/wiki/Road_racing_cyclist" title="Road racing cyclist">road racing cyclist</a> from <a href="/wiki/Colombia" title="Colombia">Colombia</a>.</p>\n<h2><span class="mw-headline" id="Career">Career</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=%C3%81lvaro_Sierra&action=edit&section=1" title="Edit section: Career">edit</a><span class="mw-editsection-bracket">]</span></span></h2>\n<div class="div-col columns column-count column-count-2" style="-moz-column-count: 2; -webkit-column-count: 2; column-count: 2;">\n<dl>\n<dt>1990</dt>\n<dd>6th in General Classification GP Internacional de Café, Bogota (COL)</dd>\n<dt>1991</dt>\n<dd>1st in General Classification <a class="new" href="/w/index.php?title=1991_Vuelta_a_Colombia&action=edit&redlink=1" title="1991 Vuelta a Colombia (page does not exist)">Vuelta a Colombia</a> (COL)</dd>\n<dt>1993</dt>\n<dd>8th in General Classification <a href="/wiki/1993_Vuelta_a_Colombia" title="1993 Vuelta a Colombia">Vuelta a Colombia</a> (COL)</dd>\n<dt>1994</dt>\n<dd>2nd in General Classification <a href="/wiki/1994_Vuelta_a_Colombia" title="1994 Vuelta a Colombia">Vuelta a Colombia</a> (COL)</dd>\n<dt>1995</dt>\n<dd>3rd in Stage 4 <a href="/wiki/1995_Vuelta_a_Colombia" title="1995 Vuelta a Colombia">Vuelta a Colombia</a>, Manizales (COL)</dd>\n<dd>2nd in Stage 8 Vuelta a Colombia, Buenaventura (COL)</dd>\n<dd>3rd in Stage 11 Vuelta a Colombia, Ibagué (COL)</dd>\n<dd>3rd in General Classification Vuelta a Colombia (COL)</dd>\n<dt>1996</dt>\n<dd>2nd in Stage 9 <a href="/wiki/1996_Cl%C3%A1sico_RCN" title="1996 Clásico RCN">Clásico RCN</a>, Santa Helena (COL)</dd>\n<dd>6th in General Classification <a href="/wiki/1996_Cl%C3%A1sico_RCN" title="1996 Clásico RCN">Clásico RCN</a> (COL)</dd>\n<dt>1997</dt>\n<dd>7th in General Classification <a href="/wiki/1997_Cl%C3%A1sico_RCN" title="1997 Clásico RCN">Clásico RCN</a> (COL)</dd>\n<dd>7th in General Classification <a href="/wiki/1997_Vuelta_a_Colombia" title="1997 Vuelta a Colombia">Vuelta a Colombia</a> (COL)</dd>\n<dt>1998</dt>\n<dd>1st in General Classification Vuelta a Antioquia (COL)</dd>\n<dd>1st in General Classification Vuelta a Boyacà (COL)</dd>\n<dd>1st in Stage 9 <a href="/wiki/1998_Cl%C3%A1sico_RCN" title="1998 Clásico RCN">Clásico RCN</a>, Bogotá (COL)</dd>\n<dd>5th in General Classification <a href="/wiki/1998_Cl%C3%A1sico_RCN" title="1998 Clásico RCN">Clásico RCN</a> (COL)</dd>\n<dt>1999</dt>\n<dd>1st in General Classification Vuelta a Boyacà (COL)</dd>\n<dd>7th in General Classification <a href="/wiki/1999_Vuelta_a_Colombia" title="1999 Vuelta a Colombia">Vuelta a Colombia</a> (COL)</dd>\n<dd>1st in Stage 3 <a href="/wiki/1999_Cl%C3%A1sico_RCN" title="1999 Clásico RCN">Clásico RCN</a>, Alto de Patios (COL)</dd>\n<dd>2nd in Stage 7 Clasico RCN, El Cable (COL)</dd>\n<dd>2nd in General Classification Clasico RCN (COL)</dd>\n<dt>2000</dt>\n<dd>2nd in Stage 15 <a href="/wiki/2000_Vuelta_a_Colombia" title="2000 Vuelta a Colombia">Vuelta a Colombia</a>, Tunja (COL)</dd>\n<dd>1st in Stage 2 Vuelta a Boyacà, El Humilladero (COL)</dd>\n<dd>2nd in Stage 3 Vuelta a Boyacà, Mongui (COL)</dd>\n<dd>2nd in General Classification Vuelta a Boyacá (COL)</dd>\n<dd>5th in General Classification <a href="/wiki/2000_Cl%C3%A1sico_RCN" title="2000 Clásico RCN">Clásico RCN</a> (COL)</dd>\n<dd>3rd in General Classification <a href="/wiki/2000_Vuelta_a_Venezuela" title="2000 Vuelta a Venezuela">Vuelta a Venezuela</a> (VEN)</dd>\n<dt>2001</dt>\n<dd>1st in General Classification Vuelta a Boyacà (COL)</dd>\n<dd>3rd in Stage 7 Vuelta al Tachira, Circuito en Mérida con llegada en Tovar (VEN)</dd>\n<dt>2002</dt>\n<dd>2nd in Stage 4 Clasica del Meta, Alto de Buenavista (COL)</dd>\n<dd>1st in Stage 4 Vuelta al Tolima, Ibagué (COL)</dd>\n<dd>3rd in Stage 5 Vuelta a Boyacà, Toca (COL)</dd>\n<dd>2nd in General Classification Vuelta a Boyacà (COL)</dd>\n<dd>3rd in Stage 6 Vuelta a Boyacà, Tunja (COL)</dd>\n<dt>2003</dt>\n<dd>1st in General Classification Doble Sucre Potosí GP Cemento Fancesa (BOL)</dd>\n<dd>1st in Stage 1 Clasica Integración de la Guadua-Gobernación de Risaralda, Marsella (COL)</dd>\n<dd>2nd in Stage 2 Clasica Integración de la Guadua-Gobernación de Risaralda, Apia (COL)</dd>\n<dd>1st in General Classification Clasica Integración de la Guadua-Gobernación de Risaralda (COL)</dd>\n<dd>3rd in Stage 3 Vuelta a Antioquia, Jerico (COL)</dd>\n<dd>1st in Stage 4 Vuelta a Antioquia, Alto de El Escobero (COL)</dd>\n<dd>2nd in General Classification Vuelta a Antioquia (COL)</dd>\n<dd>2nd in Stage 5 <a href="/wiki/2003_Vuelta_a_Colombia" title="2003 Vuelta a Colombia">Vuelta a Colombia</a>, El Escobero (COL)</dd>\n<dd>2nd in Stage 13 Vuelta a Colombia, Cali (COL)</dd>\n<dd>3rd in General Classification Vuelta a Colombia (COL)</dd>\n<dd>3rd in Stage 4 Vuelta a Boyacà, Jenesano (COL)</dd>\n<dd>3rd in Stage 5 Vuelta a Boyacà, Tunja (COL)</dd>\n<dd>2nd in Stage 7 <a href="/wiki/2003_Cl%C3%A1sico_RCN" title="2003 Clásico RCN">Clásico RCN</a>, Tunja (COL)</dd>\n<dd>3rd in Stage 8 Clasico RCN, Alto de Patios (COL)</dd>\n<dd>2nd in General Classification Clasico RCN (COL)</dd>\n<dd>1st in Stage 3 Doble Copacabana GP Fides, La Paz (BOL)</dd>\n<dd>1st in Stage 4 Doble Copacabana GP Fides, Viarcha (BOL)</dd>\n<dd>2nd in Stage 5 part b Doble Copacabana GP Fides, Copacabana (BOL)</dd>\n<dd>1st in General Classification Doble Copacabana GP Fides (BOL)</dd>\n<dd>2nd in Stage 4 <a class="mw-redirect" href="/wiki/Vuelta_a_Costa_Rica" title="Vuelta a Costa Rica">Vuelta a Costa Rica</a>, Ciudad Quesada (CRC)</dd>\n<dd>1st in Stage 7 Vuelta a Costa Rica, Barva (CRC)</dd>\n<dd>2nd in Stage 8 Vuelta a Costa Rica, Cascajal de Coronado (CRC)</dd>\n<dd>1st in Stage 10 Vuelta a Costa Rica, Pérez Zeledón (CRC)</dd>\n<dd>3rd in General Classification Vuelta a Costa Rica (CRC)</dd>\n<dt>2004</dt>\n<dd>2nd in Stage 1 Clásica Club Deportivo Boyacá, Alto del Topo (COL)</dd>\n<dd>1st in General Classification Clásica Club Deportivo Boyacá (COL)</dd>\n<dd>1st in Stage 2 Vuelta a Cundinamarca, Fusagasugá (COL)</dd>\n<dd>1st in General Classification Vuelta a Cundinamarca (COL)</dd>\n<dd>5th in General Classification <a href="/wiki/2004_Cl%C3%A1sico_RCN" title="2004 Clásico RCN">Clásico RCN</a> (COL)</dd>\n<dt>2005</dt>\n<dd>1st in Stage 1 Doble Sucre Potosí GP Cemento Fancesa, Potosí (BOL)</dd>\n<dd>1st in Stage 2 Doble Sucre Potosí GP Cemento Fancesa, Potosí (BOL)</dd>\n<dd>1st in General Classification Doble Sucre Potosí GP Cemento Fancesa (BOL)</dd>\n<dd>1st in Stage 3 Vuelta a Boyacà, Saboyá (COL)</dd>\n<dd>3rd in Stage 4 Vuelta a Boyacà, Cucaita (COL)</dd>\n<dd>2nd in Stage 3 <a href="/wiki/2005_Vuelta_a_Colombia" title="2005 Vuelta a Colombia">Vuelta a Colombia</a>, Armenia (COL)</dd>\n<dd>3rd in Stage 8 Vuelta a Colombia, Jerico (COL)</dd>\n<dd>3rd in Stage 13 Vuelta a Colombia, La Y (COL)</dd>\n<dd>3rd in General Classification Vuelta a Colombia (COL)</dd>\n<dd>3rd in General Classification GP Cootranspensilvania (COL)</dd>\n<dd>3rd in Stage 7 <a href="/wiki/2005_Cl%C3%A1sico_RCN" title="2005 Clásico RCN">Clásico RCN</a>, Armenia (COL)</dd>\n<dd>2nd in General Classification Clasico RCN (COL)</dd>\n<dd>3rd in Stage 8 Clasico RCN, Manizales (COL)</dd>\n<dd>2nd in Stage 2 Doble Copacabana GP Fides, La Paz (BOL)</dd>\n<dd>1st in Stage 4 Doble Copacabana GP Fides, Viacha (BOL)</dd>\n<dt>2006</dt>\n<dd>2nd in General Classification Doble Sucre Potosí GP Cemento Fancesa (BOL)</dd>\n<dd>1st in Stage 8 <a href="/wiki/2006_Vuelta_a_Colombia" title="2006 Vuelta a Colombia">Vuelta a Colombia</a>, Armenia (COL)</dd>\n<dd>1st in Stage 14 Vuelta a Colombia, Alto del Escobero (COL)</dd>\n<dd>3rd in General Classification Vuelta a Colombia (COL)</dd>\n<dd>2nd in Stage 1 Vuelta a Boyacà, Boyaca (COL)</dd>\n<dd>1st in Stage 4 Doble Copacabana GP Fides, Viacha (BOL)</dd>\n<dd>3rd in General Classification Doble Copacabana GP Fides (BOL)</dd>\n<dd>6th in General Classification <a href="/wiki/2006_Cl%C3%A1sico_RCN" title="2006 Clásico RCN">Clásico RCN</a> (COL)</dd>\n<dt>2007</dt>\n<dd>3rd in Stage 2 Doble Sucre Potosí GP Cemento Fancesa, Potosi (BOL)</dd>\n<dd>3rd in General Classification Doble Sucre Potosí GP Cemento Fancesa (BOL)</dd>\n<dt>2008</dt>\n<dd>3rd in Prologue Vuelta a Cundinamarca, Cogua (COL)</dd>\n<dd>2nd in General Classification Vuelta a Cundinamarca (COL)</dd>\n<dd>4th in General Classification Vuelta a Boyacà (COL)</dd>\n<dd>2nd in Stage 6 Vuelta a Boyacà, Tunja (COL)</dd>\n<dd>2nd in Stage 5 <a href="/wiki/Vuelta_a_Bolivia" title="Vuelta a Bolivia">Vuelta a Bolivia</a>, Oruro (BOL)</dd>\n<dd>1st in Stage 7 part b Vuelta a Bolivia, Copacabana (BOL)</dd>\n<dd>3rd in General Classification Vuelta a Bolivia (BOL)</dd>\n<dd>3rd in Stage 8 part a Vuelta a Bolivia, San Pablo de Tiquina (BOL)</dd>\n<dd>2nd in Stage 3 Vuelta Ciclista a la Republica del Ecuador, Quito (ECU)</dd>\n<dd>2nd in Stage 5 Vuelta Ciclista a la Republica del Ecuador, Riobamba (ECU)</dd>\n<dd>2nd in General Classification Vuelta Ciclista a la Republica del Ecuador (ECU)</dd>\n</dl>\n</div>\n<h2><span class="mw-headline" id="References">References</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=%C3%81lvaro_Sierra&action=edit&section=2" title="Edit section: References">edit</a><span class="mw-editsection-bracket">]</span></span></h2>\n<ul>\n<li><a class="external text" href="http://www.cyclingarchives.com/coureurfiche.php?coureurid=12567" rel="nofollow">Álvaro Sierra profile</a> at <i>Cycling Archives</i></li>\n</ul>\n<!-- \nNewPP limit report\nParsed by mw1288\nCached time: 20170212142643\nCache expiry: 2592000\nDynamic content: false\nCPU time usage: 0.048 seconds\nReal time usage: 0.083 seconds\nPreprocessor visited node count: 173/1000000\nPreprocessor generated node count: 0/1500000\nPost‐expand include size: 1801/2097152 bytes\nTemplate argument size: 85/2097152 bytes\nHighest expansion depth: 7/40\nExpensive parser function count: 0/500\nLua time usage: 0.009/10.000 seconds\nLua memory usage: 731 KB/50 MB\n-->\n<!--\nTransclusion expansion time report (%,ms,calls,template)\n100.00% 67.444 1 -total\n 59.19% 39.923 1 Template:Cycling_archives\n 28.55% 19.255 1 Template:Spanish_name_2\n 25.22% 17.009 1 Template:Hatnote\n 10.56% 7.121 1 Template:WikidataCheck\n 9.98% 6.733 1 Template:PAGENAMEBASE\n 7.60% 5.124 1 Template:Palmares_start\n 5.77% 3.893 1 Template:Colbegin\n 4.22% 2.843 1 Template:Palmares_end\n 2.69% 1.815 1 Template:Colend\n-->\n<!-- Saved in parser cache with key enwiki:pcache:idhash:24558666-0!*!0!!*!*!* and timestamp 20170212142643 and revision id 729711134\n -->\n<noscript><img alt="" height="1" src="//en.wikipedia.org/wiki/Special:CentralAutoLogin/start?type=1x1" style="border: none; position: absolute;" title="" width="1"/></noscript></div> <div class="printfooter">\n\t\t\t\t\t\tRetrieved from "<a dir="ltr" href="https://en.wikipedia.org/w/index.php?title=Álvaro_Sierra&oldid=729711134">https://en.wikipedia.org/w/index.php?title=Álvaro_Sierra&oldid=729711134</a>"\t\t\t\t\t</div>\n<div class="catlinks" data-mw="interface" id="catlinks"><div class="mw-normal-catlinks" id="mw-normal-catlinks"><a href="/wiki/Help:Category" title="Help:Category">Categories</a>: <ul><li><a href="/wiki/Category:1967_births" title="Category:1967 births">1967 births</a></li><li><a href="/wiki/Category:Living_people" title="Category:Living people">Living people</a></li><li><a href="/wiki/Category:People_from_Sogamoso" title="Category:People from Sogamoso">People from Sogamoso</a></li><li><a href="/wiki/Category:Colombian_male_cyclists" title="Category:Colombian male cyclists">Colombian male cyclists</a></li><li><a href="/wiki/Category:Vuelta_a_Colombia_stage_winners" title="Category:Vuelta a Colombia stage winners">Vuelta a Colombia stage winners</a></li></ul></div><div class="mw-hidden-catlinks mw-hidden-cats-hidden" id="mw-hidden-catlinks">Hidden categories: <ul><li><a href="/wiki/Category:Cycling_Archives_ID_(cyclist)_same_as_Wikidata" title="Category:Cycling Archives ID (cyclist) same as Wikidata">Cycling Archives ID (cyclist) same as Wikidata</a></li></ul></div></div> <div class="visualClear"></div>\n</div>\n</div>'
This operation is quite slow and CPU-intensive. It looks like using as many processes are there are available processors speeds things up.
Finding Common Tags¶
In [33]:
from bs4 import BeautifulSoup
def count_tags(html):
soup = BeautifulSoup(html, 'html.parser')
tags = {}
for tag in soup.find_all():
if tag.name not in tags:
tags[tag.name] = 0
tags[tag.name] += 1
return tags
start = time.time()
pool = concurrent.futures.ProcessPoolExecutor(max_workers=3)
tags = pool.map(count_tags, parsed)
tags = list(tags)
tag_counts = {}
for tag in tags:
for k,v in tag.items():
if k not in tag_counts:
tag_counts[k] = 0
tag_counts[k] += v
end = time.time()
print(end - start)
tag_counts
71.57306599617004
Out[33]:
{'a': 498830,
'abbr': 11536,
'annotation': 205,
'area': 138,
'audio': 8,
'b': 45291,
'bdi': 34,
'big': 416,
'blockquote': 148,
'br': 15599,
'caption': 609,
'center': 657,
'cite': 11605,
'code': 281,
'dd': 3761,
'del': 6,
'div': 88787,
'dl': 1425,
'dt': 953,
'font': 44,
'h1': 2997,
'h2': 12336,
'h3': 2720,
'h4': 405,
'h5': 26,
'h6': 1,
'hr': 240,
'i': 55074,
'img': 24457,
'li': 263520,
'map': 9,
'math': 205,
'mfrac': 181,
'mi': 1538,
'mn': 657,
'mo': 1399,
'mover': 14,
'mrow': 1302,
'mspace': 65,
'msqrt': 21,
'mstyle': 214,
'msub': 319,
'msubsup': 56,
'msup': 163,
'mtable': 4,
'mtd': 93,
'mtext': 13,
'mtr': 13,
'munder': 7,
'munderover': 17,
'noscript': 2997,
'ol': 2626,
'p': 24099,
'pre': 12,
'q': 162,
'rb': 16,
'rp': 32,
'rt': 16,
'ruby': 16,
's': 76,
'samp': 2,
'semantics': 205,
'small': 9415,
'source': 8,
'span': 218982,
'strong': 1847,
'sub': 547,
'sup': 36301,
'table': 13114,
'td': 175989,
'th': 46258,
'time': 34,
'tr': 84116,
'tt': 7,
'u': 110,
'ul': 32928,
'wbr': 277}
Based on our findings, it looks like there are quite a few td, a, li, and span tags. This indicates that articles tend to have lots of links, along with lists and tables. Links are the most numerous tag, which indicates how interconnected articles on Wikipedia are.
Finding Common Words¶
In [40]:
from bs4 import BeautifulSoup
from collections import Counter
import re
def count_words(html):
soup = BeautifulSoup(html, 'html.parser')
words = {}
text = soup.get_text()
text = re.sub("\W+", " ", text.lower())
words = text.split(" ")
words = [w for w in words if len(w) >= 5]
return Counter(words).most_common(10)
start = time.time()
pool = concurrent.futures.ProcessPoolExecutor(max_workers=3)
words = pool.map(count_words, parsed)
words = list(words)
word_counts = {}
for wc in words:
for word, count in wc:
if word not in word_counts:
word_counts[word] = 0
word_counts[word] += 1
end = time.time()
print(end - start)
word_counts
133.99117708206177
Out[40]:
{'junior': 8,
'prannathji': 1,
'touring': 1,
'sofia': 1,
'patrick': 5,
'twice': 1,
'managers': 3,
'agostini': 1,
'domination': 1,
'billième': 1,
'kavčič': 1,
'dönhoff': 1,
'uprising': 1,
'moshe': 1,
'bangladesh': 3,
'muntaner': 1,
'mayor': 11,
'beasley': 1,
'zeitweiser': 1,
'first': 100,
'gives': 1,
'films1940s': 1,
'januszkowo': 1,
'minesweeper': 2,
'commons': 6,
'83222': 1,
'rayon': 2,
'humorist': 1,
'hercules': 1,
'encarnaçao': 1,
'calling': 2,
'today': 3,
'kazuki': 1,
'zoltán': 1,
'fortified': 1,
'martinez': 1,
'båstad': 1,
'presidential': 5,
'contributor': 1,
'trăng': 1,
'preparatory': 1,
'governor': 12,
'pietism': 1,
'least': 1,
'sulfonic': 1,
'manipuli': 1,
'scindalmota': 1,
'colliery': 1,
'birchall': 1,
'plotinus': 1,
'narasaraopet': 1,
'awareness': 2,
'willimon': 1,
'appear': 1,
'monadenia': 1,
'antioquia': 2,
'polynomials': 1,
'kitplanes': 1,
'chiriguelo': 1,
'asteraceae': 2,
'nadia': 1,
'thoracic': 1,
'entrance': 1,
'chiudinelli': 2,
'wilcox': 1,
'welfare': 2,
'choice': 1,
'cricoid': 1,
'zielona': 1,
'greyish': 2,
'naghizadeh': 1,
'arhndt': 1,
'vladimir': 1,
'flyin': 1,
'vilnius': 2,
'inflanty': 1,
'guaraldi': 1,
'viticultural': 1,
'scholars': 1,
'nagar': 5,
'hepburn': 1,
'reports': 1,
'1357883': 1,
'artificial': 1,
'biological': 2,
'francesco': 1,
'marguérite': 1,
'arxiv': 2,
'billion': 1,
'morgana': 1,
'confederation': 1,
'bahia': 2,
'brăila': 1,
'giuliani': 1,
'veronica': 1,
'sunde': 1,
'scoville': 1,
'surrounding': 1,
'chaun': 1,
'makindye': 1,
'derek': 1,
'regiments': 1,
'bosnia': 6,
'southend': 1,
'taylour': 1,
'waller': 1,
'opposite': 1,
'consultant': 1,
'ballyhale': 1,
'worcestershire': 1,
'godavari': 1,
'araneae': 1,
'physician': 1,
'draft': 10,
'raith': 1,
'congo': 1,
'paraguay': 2,
'highest': 5,
'argos': 1,
'citation': 9,
'chung': 1,
'erigeron': 1,
'ramirez': 1,
'fubinaca': 1,
'jordan': 3,
'iyama': 1,
'anatolia': 1,
'eugenio': 1,
'disney': 3,
'nacional': 2,
'funen': 1,
'luehderi': 1,
'urodilatin': 1,
'background': 1,
'vijay': 2,
'needs': 1,
'patriots': 1,
'permanent': 4,
'recuay': 1,
'clinic': 1,
'imperialis': 1,
'seibu': 1,
'ćetković': 1,
'wolfe': 1,
'fernanda': 1,
'scientist': 2,
'aminonaphthalenesulfonic': 1,
'vittra': 1,
'other': 38,
'zgierz': 2,
'bluegrass': 2,
'catalog': 2,
'nyblom': 1,
'44333': 1,
'damsa': 1,
'forever': 1,
'advocates': 1,
'heckstall': 1,
'unincorporated': 17,
'munich': 3,
'avalon': 1,
'snakebite': 1,
'porrit': 1,
'ellison': 1,
'debian': 1,
'young': 14,
'nuway': 1,
'tyson': 1,
'bexley': 1,
'boehringer': 1,
'franklin': 2,
'pyrénées': 1,
'telescope': 1,
'metropolitan': 4,
'olfactory': 1,
'cardinals': 3,
'bausch': 1,
'middlesbrough': 3,
'score': 5,
'henares': 1,
'flowered': 1,
'truck': 2,
'naichau': 1,
'production': 19,
'paschal': 1,
'jessen': 1,
'lebanon': 4,
'ratchaburi': 1,
'glazman': 1,
'daniels': 1,
'tottori': 1,
'información': 1,
'genome': 2,
'moscow': 6,
'nagashi': 1,
'abaúj': 1,
'allsvenskan': 1,
'vries': 1,
'poultry': 1,
'culkin': 1,
'chase': 1,
'ralph': 1,
'times': 22,
'gould': 1,
'borsod': 1,
'ghriss': 1,
'surgeon': 3,
'troglodytarum': 1,
'velika': 1,
'docking': 1,
'islam': 2,
'underground': 1,
'grackle': 1,
'points': 6,
'clean': 3,
'vanuatu': 1,
'pompey': 1,
'jarosław': 1,
'varus': 1,
'jaromír': 1,
'bibcode': 1,
'reader': 1,
'identifierswikipedia': 43,
'envelope': 1,
'wimberg': 1,
'xhcaa': 1,
'farida': 1,
'settlers': 1,
'ramanathan': 1,
'decimal': 1,
'stjørdal': 1,
'gender': 2,
'kamen': 1,
'arčikauskas': 1,
'simod': 1,
'wildlife': 4,
'holidays': 1,
'lighting': 1,
'kummerow': 1,
'siniscalco': 1,
'litera': 1,
'spookey': 1,
'member': 21,
'wilco': 1,
'songs': 23,
'abeno': 1,
'dordogne': 2,
'sciences': 2,
'maanikya': 1,
'000000002016': 1,
'backs': 1,
'weapons': 2,
'spiel': 1,
'kirklees': 1,
'bruses': 1,
'sidéradougou': 1,
'studios': 4,
'vincent': 2,
'mandel': 1,
'named': 4,
'mangalore': 1,
'mickey': 1,
'salma': 1,
'lawsuit': 1,
'pietismus': 1,
'kalangis': 1,
'higgins': 1,
'tunisia': 2,
'vetriswaran': 1,
'dolni': 2,
'activities': 1,
'patanga': 1,
'coulommiers': 1,
'châtillon': 2,
'capriccio': 1,
'sędki': 1,
'accessory': 1,
'turret': 1,
'visitors': 2,
'magazine': 17,
'yvelines': 1,
'caney': 1,
'bathurst': 1,
'brenda': 2,
'muğanlı': 1,
'detroit': 5,
'parrots': 1,
'railways': 1,
'rolling': 1,
'59611': 1,
'köping': 1,
'ramachandran': 1,
'larvae': 6,
'likely': 1,
'pochyta': 1,
'mascara': 1,
'canot': 1,
'directive': 2,
'eighty': 1,
'bahuguna': 1,
'peptide': 2,
'macmillan': 1,
'furkan': 1,
'cable': 2,
'keonjhar': 1,
'boogie': 1,
'szczawin': 1,
'dašić': 1,
'antennata': 1,
'zschokke': 1,
'backyard': 1,
'sirusho': 1,
'pippo': 1,
'creative': 1,
'tropische': 1,
'chenar': 1,
'original': 19,
'gosling': 1,
'overstreet': 2,
'chisocheton': 1,
'öland': 1,
'chaux': 2,
'goiás': 2,
'ground': 3,
'event': 12,
'namhaedo': 1,
'teacher': 1,
'sylvian': 1,
'palmer': 5,
'writer': 11,
'macrobertson': 1,
'javier': 1,
'students': 20,
'helmond': 1,
'twiggy': 1,
'73917': 1,
'rescue': 1,
'daniele': 1,
'innings': 1,
'rhialto': 1,
'dinamo': 3,
'edwin': 1,
'moderni': 1,
'shrek': 1,
'haider': 1,
'viamala': 1,
'pedro': 2,
'cheddar': 1,
'exploratorium': 1,
'bayfield': 1,
'subdivision': 1,
'sevens': 2,
'nelonen': 1,
'pergamus': 1,
'requires': 2,
'santa': 19,
'mengs': 1,
'vitaly': 1,
'bombardment': 1,
'gimhae': 1,
'deshamanya': 1,
'maine': 4,
'rivals': 1,
'ponder': 1,
'jeffs': 1,
'spicules': 1,
'unicode': 1,
'tomorrow': 1,
'cincinnati': 5,
'amborellaceae': 1,
'analog': 1,
'mediaș': 1,
'roxburgh': 1,
'huddersfield': 1,
'appenzell': 1,
'turista': 1,
'branches': 1,
'kumamoto': 1,
'aliabad': 4,
'sloop': 1,
'montana': 5,
'funny': 1,
'document': 1,
'łosie': 1,
'66083': 1,
'later': 7,
'atoxica': 1,
'paranhos': 1,
'former': 10,
'qualifier': 2,
'competed': 1,
'witzenhausen': 1,
'latin': 11,
'adams': 3,
'scales': 1,
'splash': 1,
'gorkha': 1,
'trojans': 2,
'floor': 2,
'hampson': 3,
'precinct': 1,
'arterial': 1,
'fidélis': 1,
'cutervo': 1,
'danmark': 1,
'groups': 3,
'veloso': 1,
'emulations': 1,
'pontiac': 1,
'dundas': 1,
'ariarathes': 1,
'channel': 8,
'description': 4,
'innocent': 1,
'sequences': 1,
'fuscozonata': 1,
'maharaj': 1,
'networking': 1,
'wizard': 2,
'criterium': 1,
'gasht': 1,
'acosta': 1,
'loving': 1,
'guarro': 1,
'bigelovii': 1,
'inches': 1,
'stian_aker': 1,
'gardner': 3,
'mudramothiram': 1,
'cobreloa': 1,
'mahony': 1,
'lithophila': 1,
'concepción': 1,
'smeaton': 1,
'haven': 2,
'reviews': 4,
'cindy': 1,
'references': 34,
'dzahadjou': 1,
'sicily': 1,
'garrisson': 1,
'schneider': 1,
'psychology': 5,
'warsaw': 2,
'guangde': 1,
'nominee': 1,
'muirí': 1,
'written': 10,
'leeuwen': 1,
'chaharduli': 1,
'tachinidae': 2,
'incumbent': 1,
'diego': 4,
'ennico': 1,
'kazan': 2,
'italiane': 1,
'coupier': 1,
'riffle': 1,
'saxophone': 1,
'fleet': 7,
'residence': 2,
'auryn': 1,
'hotels': 1,
'association': 10,
'histoplasmosis': 1,
'leuke': 1,
'imphal': 1,
'baloch': 1,
'asheqlu': 1,
'supernova': 1,
'namhae': 2,
'zebina': 1,
'mazowiecki': 1,
'taluka': 2,
'rican': 1,
'subcutaneous': 1,
'admiral': 2,
'alakbarova': 1,
'nerve': 1,
'lyrics': 3,
'porto': 1,
'finnmark': 1,
'transistor': 1,
'pilot': 5,
'anwar': 1,
'mafeteng': 1,
'bridge': 13,
'tryavna': 2,
'doble': 2,
'maritime': 3,
'circumcarinata': 1,
'manor': 1,
'grichka': 1,
'planetary': 1,
'leprieuri': 1,
'plants': 4,
'sarojini': 1,
'lough': 1,
'safety': 2,
'meneng': 1,
'kartli': 1,
'badgers': 1,
'opinions': 1,
'contralateral': 1,
'tiranë': 1,
'bethoncourt': 1,
'kapinovo': 1,
'civil': 17,
'those': 1,
'estrone': 1,
'babak': 1,
'brian': 4,
'leaders': 7,
'mossman': 1,
'carley': 1,
'honey': 2,
'normandin': 1,
'known': 14,
'hydroxynaphthalene': 1,
'marcus': 1,
'personalities': 1,
'kapoor': 3,
'government': 29,
'ghisallo': 1,
'regional': 10,
'reaction': 1,
'works': 13,
'neville': 1,
'mausoleum': 1,
'icelandic': 1,
'methodist': 1,
'lakshmanan': 1,
'script': 1,
'three': 11,
'herzegovina': 7,
'runoff': 1,
'dawson': 1,
'eliskases': 1,
'vinca': 1,
'television': 50,
'bukovica': 1,
'reward': 1,
'noctuoidea': 1,
'jetpack': 1,
'picture': 2,
'kildare': 1,
'rheumatoid': 1,
'romagna': 1,
'phong': 1,
'abbas': 2,
'season': 61,
'dictionary': 4,
'peparethos': 1,
'brugnoli': 1,
'peptides': 1,
'passive': 1,
'spectra': 2,
'chandan': 1,
'circuit': 5,
'alvord': 1,
'keisling': 1,
'canberra': 1,
'adviser': 1,
'watford': 2,
'lubbock': 1,
'constant': 4,
'lantern': 1,
'pampanga': 1,
'membranacea': 1,
'partial': 1,
'vessels': 2,
'residenztheater': 1,
'inducing': 1,
'chamber': 2,
'sales': 3,
'geforce': 1,
'suburban': 2,
'kissing': 1,
'video': 24,
'center': 27,
'125th': 1,
'leyte': 1,
'christopher': 1,
'bradford': 1,
'stealing': 1,
'carracedo': 1,
'dołęgi': 1,
'commission': 8,
'homebuilding': 1,
'catholic': 21,
'whiting': 1,
'chacon': 1,
'healing': 1,
'aereon': 1,
'dasyure': 1,
'busan': 2,
'career': 82,
'bratz': 1,
'rolli': 1,
'holstein': 1,
'dewey': 1,
'utiel': 1,
'creek': 15,
'edward': 5,
'destroyer': 2,
'coalfield': 1,
'354927000': 1,
'aspietes': 1,
'clothes': 1,
'relegated': 1,
'regiment': 7,
'annunciation': 1,
'corps': 6,
'monkey': 2,
'thompson': 2,
'saudi': 3,
'bicycle': 1,
'angèle': 1,
'sentence': 1,
'brzózka': 1,
'85111': 1,
'mechanisms': 1,
'kappa': 1,
'syntomis': 1,
'larvicide': 1,
'bangkok': 3,
'observer': 1,
'uttarakhand': 1,
'rally': 3,
'heuch': 1,
'bayadh': 1,
'animals': 1,
'nicola': 1,
'feedjit': 1,
'koishiteru': 1,
'bloomfield': 1,
'thornaby': 1,
'human': 12,
'internal': 1,
'wilkes': 1,
'filmsturkish': 1,
'watch': 5,
'okoye': 1,
'fuchs': 1,
'metallurg': 1,
'sulukh': 1,
'khedoori': 1,
'coronium': 1,
'benítez': 1,
'fusiliers': 1,
'warrant': 1,
'precursor': 1,
'family': 73,
'theorem': 2,
'defence': 3,
'immunity': 2,
'kramer': 1,
'lucky': 1,
'livonia': 1,
'ereader': 1,
'israelites': 1,
'ramaranjan': 1,
'maria': 6,
'isaac': 1,
'force': 8,
'paralympic': 2,
'maribor': 1,
'tatars': 1,
'baddie': 1,
'ruins': 1,
'stade': 1,
'ryots': 1,
'worldcat': 4,
'coccidioidomycosis': 1,
'reunion': 1,
'boland': 1,
'nellie': 2,
'speed': 10,
'redwater': 1,
'bowles': 1,
'katie': 1,
'merelim': 1,
'solkan': 1,
'germar': 1,
'missing': 6,
'greek': 25,
'fulcher': 1,
'monument': 3,
'harvard': 4,
'sustainability': 1,
'summer': 30,
'bromo': 1,
'chemokine': 1,
'rainstorm': 1,
'kenneth': 2,
'straloch': 1,
'stone': 8,
'hirst': 1,
'horsey': 1,
'šumadija': 1,
'parfitt': 1,
'galaxies': 2,
'climate': 9,
'westminster': 1,
'herbert': 3,
'fungal': 1,
'giovanni': 3,
'believer': 1,
'conveyor': 1,
'bechdel': 1,
'søren': 1,
'eugamandus': 1,
'medal': 21,
'ömnögovi': 1,
'begin': 1,
'01333': 1,
'valle': 1,
'meaning': 1,
'baltimore': 4,
'gosei': 1,
'krispies': 1,
'eastern': 13,
'oplast': 1,
'serpentine': 1,
'january': 96,
'macroagelaius': 1,
'posters': 1,
'stuart': 3,
'elizabeth': 6,
'apocephalus': 1,
'philip': 1,
'sherry': 1,
'mussels': 1,
'raggett': 1,
'dream': 4,
'zhejiang': 1,
'forewings': 2,
'saves': 1,
'makkasan': 1,
'mansion': 1,
'trucks': 1,
'animated': 1,
'azerbaijani': 2,
'purged': 1,
'recke': 1,
'infections': 1,
'batted': 2,
'kosaka': 1,
'categories': 217,
'shanghai': 2,
'heroines': 1,
'laser': 1,
'always': 1,
'khikhani': 1,
'rovers': 7,
'verpelét': 1,
'germán': 1,
'evermore': 1,
'stefano': 1,
'asiab': 1,
'viola': 1,
'flour': 1,
'aviva': 1,
'volumes': 1,
'figaro': 1,
'mclaren': 1,
'gnome': 1,
'junction': 6,
'against': 11,
'lorne': 1,
'slavery': 1,
'manga': 3,
'phorids': 1,
'gospel': 1,
'wiltshire': 1,
'discretization': 1,
'headache': 1,
'transilien': 1,
'volunteer': 1,
'авени': 1,
'hyderabad': 1,
'volleyball': 5,
'beverley': 1,
'induced': 1,
'yarumal': 1,
'cells': 1,
'romance': 3,
'evraki': 1,
'tacloban': 1,
'grows': 2,
'lagunitas': 1,
'elevation': 2,
'territory': 2,
'qualifying': 2,
'contains': 3,
'economics': 4,
'deseret': 1,
'noise': 2,
'kirby': 1,
'transportation': 5,
'agripina': 1,
'smoszewo': 1,
'stiles': 1,
'scott': 6,
'andorra': 2,
'italien': 1,
'göttingen': 1,
'presenters': 1,
'luigné': 1,
'vatican': 1,
'seyyed': 1,
'midnight': 3,
'vaibbhav': 1,
'fusidic': 1,
'newport': 1,
'unusual': 1,
'casey': 1,
'payments': 1,
'pages': 2,
'mullins': 1,
'gubernatorial': 1,
'density': 1,
'tanenbaum': 1,
'exchange': 1,
'hasan': 2,
'richt': 1,
'genealogical': 2,
'000000001989': 1,
'leuty': 1,
'natural': 9,
'guineas': 1,
'carol': 1,
'policy': 2,
'woolley': 1,
'rolin': 1,
'vista': 1,
'murinus': 1,
'lawngtlai': 1,
'logan': 2,
'chapel': 3,
'banovinas': 1,
'general': 42,
'enhanced': 1,
'bresse': 1,
'fresno': 3,
'porch': 1,
'fisher': 2,
'anish': 1,
'equestrian': 1,
'smilax': 1,
'drain': 1,
'municipality': 32,
'chapter': 2,
'surnames': 1,
'steinbauer': 1,
'faber': 3,
'czech': 8,
'international': 45,
'choral': 2,
'class': 30,
'94750': 1,
'moginie': 1,
'houghton': 1,
'cymru': 1,
'astoria': 2,
'36528': 1,
'oznoz': 1,
'italy': 12,
'villers': 6,
'autism': 1,
'touch': 2,
'svalbard': 1,
'rapper': 1,
'spanish': 34,
'breads': 1,
'taproot': 1,
'founder': 1,
'braunschweig': 1,
'neolepetopsidae': 1,
'including': 1,
'firefox': 1,
'lincoln': 7,
'garuh': 1,
'giang': 2,
'eleuteri': 1,
'match': 12,
'iwaki': 1,
'osteoporosis': 1,
'préliminaires': 1,
'couple': 1,
'armstrong': 3,
'musica': 1,
'shackleton': 1,
'funeral': 1,
'ortiz': 1,
'kyril': 1,
'zvereva': 1,
'continuity': 1,
'brasil': 1,
'nepali': 1,
'winters': 1,
'runner': 1,
'hammerstein': 1,
'hanna': 1,
'lalden': 1,
'chemo': 1,
'granduciel': 1,
'anterior': 2,
'wolfpack': 1,
'lincolnshire': 1,
'kawabe': 1,
'nueva': 1,
'jagiellonia': 1,
'friendship': 4,
'stoke': 1,
'scenic': 1,
'ricardo': 2,
'stream': 1,
'sweden': 10,
'boost': 1,
'paranaense': 1,
'torkaman': 1,
'suvarnabhumi': 1,
'anglican': 1,
'frisian': 1,
'germany': 21,
'huesca': 1,
'shaun': 1,
'propantheline': 1,
'filled': 1,
'tomakomai': 1,
'gnophaela': 1,
'lecanoromycetes': 1,
'database': 6,
'johnstown': 1,
'celta': 2,
'vaughn': 1,
'gibraltar': 1,
'mitsuki': 1,
'hairy': 1,
'ayeyarwady': 1,
'ordinary': 2,
'bruderschaft': 1,
'operative': 1,
'cocktail': 1,
'tazeh': 2,
'hasanein': 1,
'shortest': 1,
'completed': 1,
'velike': 1,
'celtic': 3,
'darvazeh': 1,
'london': 40,
'myoictis': 1,
'component': 1,
'matilda': 1,
'arabic': 8,
'radomsko': 1,
'pirama': 1,
'baxter': 1,
'gliese': 2,
'cantonese': 1,
'allegro': 1,
'brooks': 1,
'biggest': 1,
'fischli': 1,
'girolamo': 1,
'erksan': 1,
'affairs': 2,
'steamroller': 1,
'contest': 3,
'awarded': 2,
'selling': 1,
'msnbc': 1,
'pequeñas': 1,
'assault': 1,
'police': 9,
'censorship': 1,
'reloaded': 1,
'bušić': 1,
'encyclopædia': 1,
'barbus': 1,
'mobile': 6,
'finishes': 1,
'bills': 1,
'baronetcy': 1,
'kansas': 9,
'drooling': 1,
'philippines': 5,
'seine': 2,
'passing': 1,
'pregnant': 1,
'caspase': 1,
'liverpool': 1,
'green': 11,
'greenhouses': 1,
'princess': 1,
'uttar': 2,
'desmiphora': 1,
'coordinates': 56,
...}
Only selecting the top 10 words from each article speeds up performance quite a bit.