haruka_parser/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
haruka_parser/extract.py,sha256=dxVgmIN968a7LqI7wBoZuau9Y43ExVHSIkzki5OboGE,21811
haruka_parser/html_text.py,sha256=XiXDiCipWd4OqgBZNhzduJUjfgprEKoebHQl8oiZdgo,7322
haruka_parser/latex_processing.py,sha256=uwFXyeLy2AoUYaFKzyuvgrhUzB908Rcm8OlQks_vuS8,28247
haruka_parser/line_processing.py,sha256=mgzilpl7oSf2-RjRdH8oUB-evDXs6bWmOHI-lUro3yo,4494
haruka_parser/meta_processing.py,sha256=lm3xsFoMVg0ft9ized-IW5QBbb4sbHsko11sBWl6Gkk,23256
haruka_parser/readablity_go.py,sha256=KQ_qDzj8hvb-K4rX9D7i1l1t4_yl8c5i8FUSiUGTy00,1145
haruka_parser/readablity_lxml.py,sha256=fPyF-anlEYrnLT42HlFrj7JRQMvyWG6XgUGWueZYcKY,35554
haruka_parser/time_formatter.py,sha256=VA_2cmi026aSkjTMaHXG_i2CQuIcs771mKi1BxQ5wI8,14291
haruka_parser/tree_cleaning.py,sha256=-B_XtnLbVEEi3lTeNLmh0Jpwb1WO3uU2FHZJ1FdegYo,15058
haruka_parser/tree_processing.py,sha256=CYL8aNPiIvFBVPsEQsgZnfBxi1TO0sm-XUhwKc0shPg,30494
haruka_parser/utils.py,sha256=s7cJORpVnStwyfPqsE3aNWLo5Rc8reS79UURiP2lCt0,11790
haruka_parser/dictionary/Blocks.txt,sha256=BUDvlCF35pcsd17brkpQW4Nx0SrCy-0I6kx2u8lkcCw,19956
haruka_parser/dictionary/banned_selectors.txt,sha256=DExeYfVqm1giqdwfzFrUUzE4Pv_5J_tfJmt-f4PY5ak,1922
haruka_parser/dictionary/boilerplate_words.txt,sha256=-meAPbbaqO1sjMAID-k4S193UnHmOtsK8nA0_g11_uc,1851
haruka_parser/dictionary/highlightjs.py,sha256=NlU2Qb-6oPoglSKz8Lug_1IcUmecyuuUqsJ39nDmlss,9217
haruka_parser/dictionary/language.py,sha256=g7sDB5K0ukeiT-nAvI33hBp2_z36NATV5dKrszZqKG0,13520
haruka_parser/dictionary/latex_words.txt,sha256=RwNqXb_BImRzeidW7jnb1j7H4ap74ZGWpMZ-2wRRJTo,2582
haruka_parser/dictionary/public_suffix_list.txt,sha256=Fr2qwyrB8xXShS1_iiD__tMLSoSi9ToJrdbJwCraLp0,320156
haruka_parser/filter/__init__.py,sha256=L61uS7owlZCxxr30KbM5FQlgw5ndx0lDGGfQ07s07h4,310
haruka_parser/filter/_import_utils.py,sha256=Sk181Phq497ofS1_WlcNkKqim0CFiB4rBj3m7gfm6us,2322
haruka_parser/filter/base_filter.py,sha256=qbk3jjYuyu8hF3Xzap_hJGTYSCQOL6RQgIgqZcXPCRI,1187
haruka_parser/filter/c4_filters.py,sha256=IbMvX5y7G8u9n413UKKJoKSD9GjIDpO8N4bCI0Mp7bY,10601
haruka_parser/filter/data.py,sha256=ZptP5_VJ2-CbOqDyxhfOIUZLrJfV7H9tSD3-VrvS550,1253
haruka_parser/filter/fineweb_quality_filter.py,sha256=-7OSVsr8edETivuVDnUzGlnHftyj8H57HqdFSPJfldg,2848
haruka_parser/filter/gopher_quality_filter.py,sha256=Y26Edwo7sFmYuWYdI60aMA9lWMpoPmvEeuu4_cglsgs,5083
haruka_parser/filter/gopher_repetition_filter.py,sha256=n79m18RaRfumwLAO86wtH5npEWaW-bqhQzr6e90pmxc,4796
haruka_parser/filter/text.py,sha256=gH7fYyUIuNxKKjmP9w-en2XxFzRqfhxy2fNWQFUvrWw,4202
haruka_parser/filter/typeshelper.py,sha256=clVf6KkUwIb3R9ONqlJMPF1D4gJafdzZh7aMy06M22c,2708
haruka_parser/filter/url_filter.py,sha256=5haF8ytS7Hoh0Q1AjshWYEJv2n16EiHBg0U1fO4TRRo,4911
haruka_parser/filter/word_tokenizers.py,sha256=qA8hbObVsqG5Hi51XzMUV3lHKMXbnRrQM_ofiKLVfSI,13850
haruka_parser/filter/assets/banned_subwords.txt,sha256=R3BEXNjSsWSV796IvE78OlIL3A8xN9FNhc09ibGUojI,1673
haruka_parser/filter/assets/banned_words.txt,sha256=eq5RCczE2DVxZxaPo6kTMfovr9jrjMnDjMkUfCYQ-rA,1732
haruka_parser/filter/assets/soft_banned_words.txt,sha256=5QQwMKzMozsONoppOZdXa-6kxYJ52mQb_0C04CKBsGM,674
haruka_parser/filter/assets/adult/domains.gz,sha256=3sfANIwSROxTuQqTS2Fx8wkWCP-QdXcsWDUOWUBIpZA,17465343
haruka_parser/filter/assets/adult/expressions,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
haruka_parser/filter/assets/adult/urls,sha256=O5rmEUgCgGEJi7PAdlEEKW4KZY_sCA52HiD3CNCSN5k,541300
haruka_parser/filter/assets/adult/usage,sha256=Ls1-UcdWbQeWXX9cMyufmHWHTgkgLksbYrU3Voy6fI8,17
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/README,sha256=0yUcrmapNZvWjAOeOkYXKgXKnfCyfc36I65ZTWjSfsQ,8574
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/czech.pickle,sha256=W6c9KTx9eVOVa88C82lexcHw1Sfyo8OAl_VZM5T6FpA,1265552
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/danish.pickle,sha256=6il2CgqRl_UspZ54rq_FpvVdBSWPr32xcJsrnrMh7yA,1264725
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/dutch.pickle,sha256=So4ms9aMRcOOWU0Z4tVndEe_3KpjbTsees_tDpJy1zw,742624
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/english.pickle,sha256=3aN5cq6ImYpv0-PsACaXpr02KzLQUP2n18pSdocwkqo,433305
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/estonian.pickle,sha256=OGf-4mo2vbGXxkNiqhOsaD9fM_pNDSJaXVZwdYKlWh0,1596714
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/finnish.pickle,sha256=Gp4Xs9W033Y0XYErimWx2gdn7aUIbq3MEeYl7vCUKDU,1951656
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/french.pickle,sha256=3gXz1WR9PSKWYm-4P2hCjkxq1uBaAO1GlMi9yPLxl-4,583482
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/german.pickle,sha256=6rSX-ghUExMMj9D7E7kpEokwr-L2om6ocVyV33CI6Xw,1526714
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/greek.pickle,sha256=IXUqZ2L61c_kb7XEX62ahUhKDo6Bxn5q9vuXPPwn1nw,1953106
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/italian.pickle,sha256=3LJxfXvl8m6GCpLgWs9psRI6X0UnzXommpq56eZoyAU,658331
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/malayalam.pickle,sha256=H4z1isvbf0cqxAr_wTZjvkLa-0fBUDDBGt4ERMng5T0,221207
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/norwegian.pickle,sha256=5Kl_j5oDoDON10a8yJoK4PVK5DuDX6N9g-J54cp5T68,1259779
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/polish.pickle,sha256=FhJ7bRCTNCej6Q-yDpvlPh-zcf95pzDBAwc07YC5DJI,2042451
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/portuguese.pickle,sha256=uwG_fHmk6twheLvSCWZROaDks48tHET-8Jfek5VRQOA,649051
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/russian.pickle,sha256=vJhEMvvjH3AAAU-AR1AkdoiRacYPCb5UE8oJJ2sWyQk,33027
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/slovene.pickle,sha256=faxlAhKzeHs5mWwBvSCEEVST5vbsOQurYfdnUlsIuOo,832867
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/spanish.pickle,sha256=Jx3GAnxKrgVvcqm_q1ZFz2fhmL9PlyiVhE5A9ZiczcM,597831
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/swedish.pickle,sha256=QNUOva1sqodxXy4wCxIX7JLELeIFpUPMSlaQO9LJrPo,1034496
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/turkish.pickle,sha256=065H12UB0CdpiAnRLnUpLJw5KRBIhUM0KAL5Xbl2XMw,1225013
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/README,sha256=0yUcrmapNZvWjAOeOkYXKgXKnfCyfc36I65ZTWjSfsQ,8574
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/czech.pickle,sha256=ZLBzS2--jo18rHn0jR3Z-FOCTlfE41lNrddLosHZf1A,1119050
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/danish.pickle,sha256=YYnH3SVOKeK9QGp_akM2KXyJUyFHkkZqeQ6kREIjzrM,1191710
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/dutch.pickle,sha256=_aDWoT8C6ImNrsf-kj2ojiWr4IG8-nVcDgFQdcIV_kw,693759
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/english.pickle,sha256=XK03WFljkjZOO-mAPb1-vto4S2iTe0iKATZfVVG7lCw,406697
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/estonian.pickle,sha256=s2T3JTjRexRqmACa0jmoCWzmwKiwKVjAvHduzQxYol8,1499502
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/finnish.pickle,sha256=aktf9VAO6FHEVvndQNX8DYwYWciOsxeN4TF9JrfSKDM,1852226
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/french.pickle,sha256=KOOkzSlxmJs8uf00M6bxXReYHkZNsr4Dk2QxO13pTyk,553575
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/german.pickle,sha256=3cu-heIEKgGbGm43_YwVMobDi6IB-uD1v9mj90q64lw,1463575
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/greek.pickle,sha256=hdq8RKuQpfII7zf_a0iS6-fnQPcftNpHz9lUF8o-Iv0,876006
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/italian.pickle,sha256=aKlAB7Hk_9xNGhkBhcpUQsPa_rF6s50wMp6EzXSkOUc,615089
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/malayalam.pickle,sha256=H4z1isvbf0cqxAr_wTZjvkLa-0fBUDDBGt4ERMng5T0,221207
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/norwegian.pickle,sha256=T_ekbRQ4sxFFfRXXdjBguNMnCFLBhQ_XiMXO4ZTcSh0,1181271
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/polish.pickle,sha256=YkkArj3ftIVKmMXTuLHJu3GZdfM_7mHOFEHaufigBxg,1738386
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/portuguese.pickle,sha256=AqC3slw8dHHheRtmoxu7Uwr7sBYK7k_OzwEHZSBntKE,611919
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/russian.pickle,sha256=VJdi-BkAJNibURRy3yGjoTXu5dkjPmOsJE23N8LGHX4,33020
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/slovene.pickle,sha256=Uu8swO0n15s6pjXLvECtgRiDp1pLiovhrkBpcocP2GQ,734444
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/spanish.pickle,sha256=FkpQ-txaSfjsdCbq4R0xEe51K0ij7zc9R3RQERkqWYQ,562337
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/swedish.pickle,sha256=sPfVOL_VJmYzsJ6ELNkungrBDx2SO_IR4Ul5ct3Ecxg,979681
haruka_parser/filter/assets/nltk_data/tokenizers/punkt/PY3/turkish.pickle,sha256=rmjvWGNyisUzLofrH2uudy_zKhOkyqKwGlxoED6FPFs,1017038
haruka_parser/justext/__init__.py,sha256=SgPxvpWY77te8Rl1JvTLpkgma9lF9JDAVI-gb-nUjBU,269
haruka_parser/justext/__main__.py,sha256=RilmnD17NGtEpHW8x80Hvy2YNdC3dwt1OPwge2mVFlo,12600
haruka_parser/justext/_compat.py,sha256=NsOjbyhxShNR2Q-z8eslcEgU9OVYbD-5JiMAEaf2t-0,791
haruka_parser/justext/core.py,sha256=tjIHYx-ePAwhqw7rXmfmF67ow5Z2_jRyZwYxtLnSjww,20296
haruka_parser/justext/paragraph.py,sha256=WcvqzqTJCY4FPCczItEvxCSTcIGo2xSO5rUhi-WiHJ4,1667
haruka_parser/justext/utils.py,sha256=2a8dbQ3J-yPWEKDDyk3lLGp8akuzPuBOsWpAXdtVnbA,1979
haruka_parser/justext/stoplists/Afrikaans.txt,sha256=YAaLfysaS0RAej_2lVZ2WmgxlJI-xq6heCw0Vlp45tQ,1205
haruka_parser/justext/stoplists/Albanian.txt,sha256=3lViqj9iJwsmGClGLmkSCMPBhAlNRP-5UyJqYSbKAnw,3424
haruka_parser/justext/stoplists/Arabic.txt,sha256=U1UWRHQhGTtpqj4X0NDwt8o71F17tM5KYbTPr5IQLlg,30217
haruka_parser/justext/stoplists/Aragonese.txt,sha256=2-0-lJEhiQ8V2YVB2r_eNe5IwgSljVTqyfrFh3hvAUE,918
haruka_parser/justext/stoplists/Armenian.txt,sha256=G8TUjvA1xmjbSbRbE5R-F-bKcyR2sWk69Br-eOzNvhw,45410
haruka_parser/justext/stoplists/Aromanian.txt,sha256=K33xgj5s3te82MeR7vvmvAkbeQdk_6m_FbhCUKeCizc,3544
haruka_parser/justext/stoplists/Asturian.txt,sha256=WF6RIv-Pix_0RoZTb6FcYzMCTvMb84EZEHKDeaxrHLs,4379
haruka_parser/justext/stoplists/Azerbaijani.txt,sha256=xtMgJpmqcOnwBcKcjNvmK2ivF547R1ATP_mYY7Hz8QY,33201
haruka_parser/justext/stoplists/Basque.txt,sha256=jSg1EhDOWnxrjiZQ81-L2r-Dyu0w06eX_zDgdcJ1XRY,17791
haruka_parser/justext/stoplists/Belarusian.txt,sha256=hL3J_VBqlm2XP658crT78OisRAS6jF68X-w8OylaT_g,65883
haruka_parser/justext/stoplists/Belarusian_Taraskievica.txt,sha256=2va_7Hu-Uh3uhoFmWUa8WehzCCOa19BfB-Da_N1i7Ao,62122
haruka_parser/justext/stoplists/Bengali.txt,sha256=TZbovTX66wjrXWuw6KVBjyaREvxqlVJ2JWDXsfM5wXY,18721
haruka_parser/justext/stoplists/Bishnupriya_Manipuri.txt,sha256=zXCFcjTyddCpMaKpVAg2YpEQpMNgrbfbkYlLAGWyRZM,950
haruka_parser/justext/stoplists/Bosnian.txt,sha256=WdUiO46BgquLB98NUNzpiqFAVD74Ed_RBQk0TgtLM0k,16143
haruka_parser/justext/stoplists/Breton.txt,sha256=dl9l_6jOovpaj9y4phOIskwONlYYp3nxAFRFcboNQKs,1649
haruka_parser/justext/stoplists/Bulgarian.txt,sha256=ipLQ1l79BfzA79XzROEzF7v5j1LtTJbNmT1Q-dFiZnM,15206
haruka_parser/justext/stoplists/Catalan.txt,sha256=l9TE7fqEhgbV7QuBXYHLmI8Gd_cUyJwTVEnY1iNyTtE,1344
haruka_parser/justext/stoplists/Cebuano.txt,sha256=A8LaFsC28AGx5SawJRGdyZ_UY0Jt01MDaXXRnbeZuko,57
haruka_parser/justext/stoplists/Chinese.txt,sha256=nASMXAcTI-t0ZleyJxxUDgEKYhXbr_dAb4g_yPMKyuE,11133
haruka_parser/justext/stoplists/Chuvash.txt,sha256=jer_nK3q_QphH1aeM4Kj0-mIMs5fzlEHp_zIc--xr6E,35124
haruka_parser/justext/stoplists/Croatian.txt,sha256=IzH8jQcjGmXH1hEyxa9teOSIc8rTzCM0IghSIw1DRc8,17928
haruka_parser/justext/stoplists/Czech.txt,sha256=iBojQPasGZOW6xX021SWTCAcHGbH-mZ1IyfJ2Vwacrk,25564
haruka_parser/justext/stoplists/Danish.txt,sha256=Q1ip-MtVFsliZZezoc0OXl_SAIC2NBAytoKeixfOnTg,3504
haruka_parser/justext/stoplists/Dutch.txt,sha256=tAYBRTQjWqP2iEd-bbsTR7OVWQniwqwyWP4gVMIEWKU,1756
haruka_parser/justext/stoplists/English.txt,sha256=a0_FIOKxTCeooEbZzjgU2tbSihhlS_iwKaCCiiU8NCg,3123
haruka_parser/justext/stoplists/Esperanto.txt,sha256=Vh_Kfe2vSNoCpe2pWCB7uzTm0unwzhif2Q1PkuKkHtw,3657
haruka_parser/justext/stoplists/Estonian.txt,sha256=XMgWbF9bSW8fImhQmBGXpd4RO9zDcPPF3DDzmbGmCiE,50849
haruka_parser/justext/stoplists/Finnish.txt,sha256=rtxFjZmONDdrH6ZzxJXGr0S8pZuxLES-W9bQTGl-fiA,66511
haruka_parser/justext/stoplists/French.txt,sha256=oijLMSm1GGJBxEXZgfvEqKnoiNNPVBxnB-ye5KdOKMw,2656
haruka_parser/justext/stoplists/Galician.txt,sha256=yl_C03dzOh2BzY4GNWcWWai7zHjOcR44wTLSw5EFu1U,2857
haruka_parser/justext/stoplists/Georgian.txt,sha256=qWmvlMwrf7HNrTd7h7CNHVPsyXLGqJScSOaP8etHRjo,128465
haruka_parser/justext/stoplists/German.txt,sha256=XOm4uUQsNWv2hYT-uchO-RT1jY6n4qQ1Eu5FGba-4Yg,4653
haruka_parser/justext/stoplists/Greek.txt,sha256=cKMRGW41mDE7RgbUP4V3O0F3TQGuYwj-lIA0CYaFdzI,7796
haruka_parser/justext/stoplists/Gujarati.txt,sha256=dfh64awbPMLid6zy9PLiXVvmigVv0rt09rgDVi2y78g,6073
haruka_parser/justext/stoplists/Haitian.txt,sha256=IKazXYcgP6eYUTeOzgm5HELVc8Y2e9Pd7pEcmLEaBhQ,175
haruka_parser/justext/stoplists/Hebrew.txt,sha256=JqefpOyEmKqKtI0outHBY7BCa2DSjViAm5uzvf_DSaU,45229
haruka_parser/justext/stoplists/Hindi.txt,sha256=-hA9NXGIIR1fzRcyt-qAgfz6zQurGB3Pv3w8JE3VAwE,4944
haruka_parser/justext/stoplists/Hungarian.txt,sha256=ToEQRiSP96e3E5hl8lgweqSp5R5FFBn4cypRT7zr9r4,29227
haruka_parser/justext/stoplists/Icelandic.txt,sha256=YlRSbmkrCSi91UZMZqNWSG1Eb_kUi9mZaKFltOWVkpc,4813
haruka_parser/justext/stoplists/Ido.txt,sha256=-Wo2U-M4bzVqxw0AMoCXobVHYqj99cOufuLwxofIp44,249
haruka_parser/justext/stoplists/Igbo.txt,sha256=wgSggs8V8H-QxYyXs5I00_CVbtnf6dB5IXgqf8sTLj8,733
haruka_parser/justext/stoplists/Indonesian.txt,sha256=8BQ7QBHLbhedhycHCVgzaI71ufgS26nU667KDABl0a8,6758
haruka_parser/justext/stoplists/Irish.txt,sha256=mXKFmXSTfDCtjPJhpLIhgO-I1w5PEELW8bBhXamrRSI,1191
haruka_parser/justext/stoplists/Italian.txt,sha256=9k7T66mAwv4gU16nu_NyAa2uSYVx7dOsqDj4R0wQxvw,3715
haruka_parser/justext/stoplists/Javanese.txt,sha256=FqGV4x4Fhjde3O7HuXVKy6Jdvqqwe15itlmHw-YHOWA,4533
haruka_parser/justext/stoplists/Kannada.txt,sha256=1h5mCoyEnbQMLYjJUWG9W52Zjp-4pAUeKqeJdtAsj6E,161220
haruka_parser/justext/stoplists/Kazakh.txt,sha256=OG6povZOu81uqXP_wueLoIIjkNLomfdoKYJOe3kSA6o,52789
haruka_parser/justext/stoplists/Korean.txt,sha256=GgO3wwwT03DFRMo3tCju-H8f1WjPEwbVrs8mOTkgcJo,131487
haruka_parser/justext/stoplists/Kurdish.txt,sha256=i_JGxLuB7sKMic7LkGO1yeZ-Pz7VBs0ufKCx4THbXpc,3530
haruka_parser/justext/stoplists/Kyrgyz.txt,sha256=s_8NJKwx5Omxt7Dychp2WGmlARAG7P8s1zqcrZJg0ps,54729
haruka_parser/justext/stoplists/Latin.txt,sha256=Wlypj79psOZe7KWHSzuU4W8JaPNSSQrGD20gmW2BVMI,14282
haruka_parser/justext/stoplists/Latvian.txt,sha256=c5T2NdK0QGrboVgs8RjvXlNOs7GF4rsBF0Gf4QN8bE0,30561
haruka_parser/justext/stoplists/Lithuanian.txt,sha256=4mrdiNdXFdYbTIAzPrv4Mty3W6tYpiSve6LzoVRLMdw,43497
haruka_parser/justext/stoplists/Lombard.txt,sha256=gtlJ-1lw-xx9CZkbh_r4p3JnFWMrTjR0eXfyIeoDAZA,738
haruka_parser/justext/stoplists/Low_Saxon.txt,sha256=F-e4Wj9AzwRMFfGP5IEZfa6AaRATrWMlacV14N1FCu4,1051
haruka_parser/justext/stoplists/Luxembourgish.txt,sha256=Ef9WZThSkyHNpsPD8Eksla7zM4i04F_u2WNjjqHD3fA,2374
haruka_parser/justext/stoplists/Macedonian.txt,sha256=GuaEiagnaP_jMr51LRi-WA2OY9BkwbXOfzmsWSjA_s8,11982
haruka_parser/justext/stoplists/Malay.txt,sha256=yW-l4AmfdoIK2qfLCCCsFqz96G3TXVL_K0hnduncBXk,6368
haruka_parser/justext/stoplists/Malayalam.txt,sha256=YRDR2jLpZzH-rcwjFIAfjZmUaoSU6alw9B_HPuUyTTc,309082
haruka_parser/justext/stoplists/Maltese.txt,sha256=iB6gDNH3lQu_Mxqxj3IuwEj-GsjqNQS2dIiNWgyBLs4,11115
haruka_parser/justext/stoplists/Marathi.txt,sha256=mVOKvX7Q32xpLQR9vDNjWEJfZkvBPEC8b2MaPxGqZtk,39588
haruka_parser/justext/stoplists/Neapolitan.txt,sha256=afmOZyMvOXPgDtKz7_BoRiCqmYax5BHv6z-yVj6j02Y,1749
haruka_parser/justext/stoplists/Nepali.txt,sha256=A68C3knzz3S6x3_kjv_cINM_puSJl9zYeBN16P1b7G0,26543
haruka_parser/justext/stoplists/Newar.txt,sha256=InbNuDc6mI-Ce5MbETra5Olqz29ToKrcXU3JWtKfn0I,1465
haruka_parser/justext/stoplists/Norwegian_Bokmal.txt,sha256=qbPXCGsFMSxvAZeoCa_m6Ez5nWvh1SwO5onMORkN6ro,2850
haruka_parser/justext/stoplists/Norwegian_Nynorsk.txt,sha256=6RRSeP-fwJgqk11Hx4vx6PERSvtbtP7cnNO-ZczSTb4,2002
haruka_parser/justext/stoplists/Occitan.txt,sha256=1JTkyWoUeBIiN79H49V1C9H-TETc5wP3NpGjXtS15g4,3109
haruka_parser/justext/stoplists/Persian.txt,sha256=Xs6NR_tc3MWn59_iKYjbB6_H3F0BFpC_UU4MX4meang,4642
haruka_parser/justext/stoplists/Piedmontese.txt,sha256=6PSYx533uyMAHMu1pYV0ALnONt4ZQR9JNlFrzF9NDYY,419
haruka_parser/justext/stoplists/Polish.txt,sha256=nDVMQvEN3GnFqCVh3MoEVnQ_FSVJnhowknzH6yxdxv0,29632
haruka_parser/justext/stoplists/Portuguese.txt,sha256=aH_llk--M7zY9OTLDG7yUnT9nx03TWocjLAVqnPkpPE,3261
haruka_parser/justext/stoplists/Quechua.txt,sha256=vmoobb9pn0UW9TcWofdd5IBku6E0z_4tXdxBgSPDvzk,2237
haruka_parser/justext/stoplists/Romanian.txt,sha256=UQlEMU-f-8bosvd8tGYMr3jw9pxq8bLe_IW6SkFsj-A,7067
haruka_parser/justext/stoplists/Russian.txt,sha256=MhcMuaSoPy4dBSSrh4aL_2brkkisIU1kssg4VLSPlL0,77600
haruka_parser/justext/stoplists/Samogitian.txt,sha256=om5JNKBt9f2_vv_70xKk0WcrdtxYDTVS9pDRGWc56Mw,14867
haruka_parser/justext/stoplists/Serbian.txt,sha256=LKh_hHq43Vzi0RXNGD6FbTdJawTF083S3QChic9n2q4,21052
haruka_parser/justext/stoplists/Serbo_Croatian.txt,sha256=a5Wo85d5bD8vistWGcnRx8vbxN1q5_bm6BQbjJaMr8Q,17311
haruka_parser/justext/stoplists/Sicilian.txt,sha256=RY5nckmTD4eoOrEe1Te42aocsQN7pN7s5eMeD9fjY38,3167
haruka_parser/justext/stoplists/Simple_English.txt,sha256=A4Zr2ezft629DljWRI8VrjIDxoeYNZwKkQ2S2-PLZ0I,1567
haruka_parser/justext/stoplists/Slovak.txt,sha256=F-5HV_hOSLDD2ez0AnFPslKozv_nNpDPF4knqIB4CFk,28930
haruka_parser/justext/stoplists/Slovenian.txt,sha256=437xgZbJnHrgxMczPK4hBDBbgnBgpZDQyuOg8lltVXg,17179
haruka_parser/justext/stoplists/Spanish.txt,sha256=bqgGKtClj78zcJXZvz9mr6XhW_vCh0TleteQuQQrSBM,1851
haruka_parser/justext/stoplists/Sundanese.txt,sha256=eGgPn8PPDLf3uP6s73rqf2gZ7nZjEUlEr3SMNr_FZHk,5971
haruka_parser/justext/stoplists/Swahili.txt,sha256=8gkOd-YezyLcAjIT8YEs2NQWXiWm5n51Ex2DM79F0cU,2406
haruka_parser/justext/stoplists/Swedish.txt,sha256=9FqWzO7dBxgzOzKcTfwIPfq6f27fD9G4j0zOkzp48ZU,4870
haruka_parser/justext/stoplists/Tagalog.txt,sha256=NFQZmxNII1l6mJSgJMYj-V0caq3YaDXlyED8UPFrfpc,980
haruka_parser/justext/stoplists/Tamil.txt,sha256=yaTtftkQWtxpoWH_BTsI-Frps3EzcD6wSBvgYynpv6g,154484
haruka_parser/justext/stoplists/Telugu.txt,sha256=ZLA8YpTJCW0HFlO8-sE6E-5yKvXnJSnc-bj2Df6tkeI,95849
haruka_parser/justext/stoplists/Turkish.txt,sha256=SCI-76ednwWUUoL4h3xsTkNADLMLWJM6krwMduNyBCQ,25673
haruka_parser/justext/stoplists/Turkmen.txt,sha256=RCnrVv3ULkmniHYnzdfBF9BQonB_gV9eXnpVkwr43pU,27602
haruka_parser/justext/stoplists/Ukrainian.txt,sha256=YmloiSIgxO8imCOnhGMBfZSZ6M2WW2aMOR1b2ozeJdY,75370
haruka_parser/justext/stoplists/Urdu.txt,sha256=vINC72AF9Q6CwyZyhjowsZVVXI0BtGXOb762BrUktuQ,1900
haruka_parser/justext/stoplists/Uzbek.txt,sha256=8V3Og4k-TH26eNfn1WHimbSxCopV9rsiANcdFVY96W0,51738
haruka_parser/justext/stoplists/Vietnamese.txt,sha256=hFq4ajmroq1XV6o_C81zH7sYbiF239sQX8OfQdTU9Uc,1769
haruka_parser/justext/stoplists/Volapuk.txt,sha256=X3YuzJ4nGNlNe5aIOzHzPAWGoFdr4rUz2MCgVAg8WQg,533
haruka_parser/justext/stoplists/Walloon.txt,sha256=hleS3tlkZ_QaMlzMZKwO06jr5BCJuOaGtcwApE8o62Q,910
haruka_parser/justext/stoplists/Waray_Waray.txt,sha256=fJB6tnT7q3lrpq-zYRE8NfA_FF_xitoYJtBDvaW7Uzg,47
haruka_parser/justext/stoplists/Welsh.txt,sha256=H4X0b6Z62KKFNKPdOHulfFpdYQYXJ5iU5y1w_o8bVl0,3338
haruka_parser/justext/stoplists/West_Frisian.txt,sha256=YMQmQ0XMrngTptVKGpRH5WKfUBfukUi44c-6J2x2Q5I,1353
haruka_parser/justext/stoplists/Western_Panjabi.txt,sha256=PRztN-VdHQFtmQyMvMjUll5yALZNfGGd_clrUZA_WNw,2230
haruka_parser/justext/stoplists/Yoruba.txt,sha256=q4yIixQMjBCBxD3lr-klBVa4SsVJp4U6OoBskNDZf20,1748
haruka_parser/lang/blocks.py,sha256=dILCm735rf0URv9Fa7LD_U4QyVnC0ZewdayDfKBO2i4,2192
haruka_parser/lang/fasttext.py,sha256=CLAFUWGnWnFPCmW2sr3UTu9QuE4jK-DR_eVb_1CrgBE,8535
haruka_parser/lib/libparser-arm64.dylib,sha256=FbQ6E0C3o6WtIq4gUj0nSdzkbJvHWMqZMER-odMw0L0,4970914
haruka_parser/lib/libparser-x86.so,sha256=o0k7DcZwIRYZNZUwK2HX-nke4UN3R1fejuGzdAkXhsk,6992592
haruka_parser/magic_html/__init__.py,sha256=Gd8AjjW53bvr-7zLIsAbZe0f__Otjuy1h_TcezE3qwE,2339
haruka_parser/magic_html/config.py,sha256=ylfanj8IpmY8savc0QlzLYqgL9sy8Vg2013-SMd-ntk,12603
haruka_parser/magic_html/readability_plus.py,sha256=dvUXTXUj23kJOZxVEZnd2KlKh7sMYR82oX1bV2w8Opo,19376
haruka_parser/magic_html/utils.py,sha256=Fm78Et6frhDx0PBFPIurh005n2cSMCzWQWJSMAOudy4,12265
haruka_parser/magic_html/extractors/__init__.py,sha256=-yYBDkgMDSHYf_F_uX23wZsDSjrudhppJvm34su8_I4,23
haruka_parser/magic_html/extractors/article_extractor.py,sha256=DUJHwk0SJktbahRmKdgav74xg0W8WGDz1y4bgQ3M1_4,1572
haruka_parser/magic_html/extractors/base_extractor.py,sha256=fjulLDJH5W4UIHhiSmJKXKZEk13p_Vp5EqAb2cAjAZY,34646
haruka_parser/magic_html/extractors/custom_extractor.py,sha256=XfPBelY2U10YhmyvOiNy_jfQIOG56rlGWlMs3NmWx7U,1708
haruka_parser/magic_html/extractors/forum_extractor.py,sha256=bNK-q5SRX-rtbHayHzMRjrCzpXuzEzLoF_uVm5m4QJE,4620
haruka_parser/magic_html/extractors/title_extractor.py,sha256=0p1z5MBW1JLo0hr3-Sdt5xxvKE9CKoVH8mu2xgy3aWg,1886
haruka_parser/magic_html/extractors/weixin_extractor.py,sha256=8VvT9rkBPaL07Dy0mUQVNN3JrOXBP7yiEPtW-vrvOjc,3285
haruka_parser/magic_html/mmltex/README,sha256=kkyzFseu7NQA1-V0ZWL1gRVsyVrQhjW92ucoZyCeL0w,3092
haruka_parser/magic_html/mmltex/cmarkup.xsl,sha256=CAxdk8u7TLZcYVe2TB8OIZtT_bUXT3swHq1XT1UyJVY,35631
haruka_parser/magic_html/mmltex/entities.xsl,sha256=QYBp0ng0b3PTie8cai-ISPANL1YeYfXi-QaoZyv9Fps,71213
haruka_parser/magic_html/mmltex/glayout.xsl,sha256=ub5K5u2l4TG4SAprz4WE4pzKlx_3JcKgE8_4WPyvJOw,6114
haruka_parser/magic_html/mmltex/mmltex.xsl,sha256=PUivNuJSv8YCNFym46hKW1H3TF8w85Xs-7fYO0F08BM,1599
haruka_parser/magic_html/mmltex/scripts.xsl,sha256=CCPTslMNs-Mfg3i22btMJJQ5_QuAQeLOQIu0efpU0Bo,9610
haruka_parser/magic_html/mmltex/tables.xsl,sha256=_LrpfmDkxZ-MWTYydXunBxXddlUg3oZV6dSgZr5-MMI,4198
haruka_parser/magic_html/mmltex/tokens.xsl,sha256=jDf06SUQBLGNBxbo9cVD6UiRBChzeS1fKT5aVtgCF3c,10359
haruka_parser/mathml2latex/LICENSE,sha256=cvtmcEK9Vsq9O_mGJfXjzk26-AD8IOKCpmvh4LdmvFg,1064
haruka_parser/mathml2latex/README.md,sha256=AH8gPHjAOz8JNryEuxyC1ilpSmP84ixODw5-DY6CubY,5344
haruka_parser/mathml2latex/input.md,sha256=Vq8mFYFuCWxvwLFvMVv5zViGq-YninGpyC4F_MuweNM,1162
haruka_parser/mathml2latex/mathml2latex.py,sha256=sVN0Kvl_VWrC1MiernuNiUr59ituLrtVaaYxVpYdmTg,2366
haruka_parser/mathml2latex/output.md,sha256=SimZSLOAwDsd6-PMg3C8pbOZbJZaKZHCFqqpOz3q1_k,268
haruka_parser/mathml2latex/unicode_map.py,sha256=73-402KqFJ058XGi-iHIViuPsCh39iKcD_qzu8-oFsY,16341
haruka_parser/mathml2latex/mmltex/README,sha256=zX-KNup1GZghM0f1rxlBk8fczxjumpSRChp4TrN-YXw,3200
haruka_parser/mathml2latex/mmltex/README2,sha256=9xwdN31S3TocjhQQh5FzQJYzQoQk-nup-Tx5fl1id-M,457
haruka_parser/mathml2latex/mmltex/cmarkup.xsl,sha256=DkhimAATM0XSCfVOfY41-qTPoddqzOHjZ00Pynr4zQE,37707
haruka_parser/mathml2latex/mmltex/entities.xsl,sha256=TYZ5iGg0u9XlDDBBGuZiHL7MsxKc-3OsTIBAVM1GDek,107742
haruka_parser/mathml2latex/mmltex/glayout.xsl,sha256=Ztc7N1wiHaYZlo9u9iuROrIl3uIIIoo1VFIuojXq7TM,6879
haruka_parser/mathml2latex/mmltex/mmltex.xsl,sha256=BVXFbApz-9W2qRKKtBTxptK5vxG2bfB8tv9W1MP5iBI,1384
haruka_parser/mathml2latex/mmltex/scripts.xsl,sha256=f4ei0cDCW3cV-Ra7rC3kC5tRcKdjJxbSpCeQLoohtgo,13697
haruka_parser/mathml2latex/mmltex/tables.xsl,sha256=RxtNo8qDtVAg8_6BuYsafraB_0z7YDAB9D__fT9gmWs,4327
haruka_parser/mathml2latex/mmltex/tokens.xsl,sha256=j3JZRcBhAiiY8o5K3640phfLwxO8JVspCFlSttwBzJk,12373
haruka_parser/mmltex/README,sha256=lNrWsEcf7If-vWd50RusgGIVR7nW1MHO3_VOG8LIugI,3189
haruka_parser/mmltex/cmarkup.xsl,sha256=qssTbdb5_vMPFeo6NQ7cZzQ2iwhRWkJtN59dJDtsbhc,36723
haruka_parser/mmltex/entities.xsl,sha256=uNDq3O4p5u9On0la1bj3KlhOEoS_mQWXZJFeIzFiS2c,71528
haruka_parser/mmltex/glayout.xsl,sha256=sgHlr9-M-FRJrJDtxDJlylpAv6O1b2xjJdaIOsZhv_g,6333
haruka_parser/mmltex/mmltex.xsl,sha256=6KUIyFc9Np8eTbKWbrnXCJhwbmH0WLZl5QnZFVIK0Yk,1643
haruka_parser/mmltex/scripts.xsl,sha256=-qaihwEBKOOKUVa_sqmTGo2rhcmwjvXFklZt2lnrzZ8,9901
haruka_parser/mmltex/tables.xsl,sha256=RxtNo8qDtVAg8_6BuYsafraB_0z7YDAB9D__fT9gmWs,4327
haruka_parser/mmltex/tokens.xsl,sha256=lQIhRsXQ3WOHchoYHIJ0TkoI8mbeHZI-xLsk8NsRMBU,10654
haruka_parser/table_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
haruka_parser/table_processing/attribute.py,sha256=yNuERt2Z39Nu5uaqZcJlUvjI4AMzNaKQtGz99bYFBz4,5627
haruka_parser/table_processing/canvas.py,sha256=NND5PZ-ps-XbFqBdN4Rn2T8RULUlivX8uDDfSQCTxB4,11129
haruka_parser/table_processing/html_element.py,sha256=YIvEVb3DfVgMyKwHEmn8x24RAqiDN6FrxmpIqUQ7hfA,5766
haruka_parser/table_processing/html_properties.py,sha256=thnr4QyeOHwsZ9_dmJJz_6NLI3lxvgAyXsKD6mpAQrc,1420
haruka_parser/table_processing/html_state.py,sha256=4_-pH46g0xRarDgPjITNmLWSl2eImGJtTS8tbM4M4KU,6591
haruka_parser/table_processing/table_processing.py,sha256=H6APJQZwwjHIpJ9AY7kBCvEhyYBz2QeD8BTFGvmZp6Y,6209
haruka_parser/table_processing/tags/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
haruka_parser/table_processing/tags/a_tag.py,sha256=g_bAvWg6io-H4XB3gkBTQDrLr2SdSChIBKB6lfaHOvE,672
haruka_parser/table_processing/tags/br_tag.py,sha256=GURaIq2SZpLB8zceFxVPFIScbXx_l7IOLJNZlAKV6is,264
haruka_parser/table_processing/tags/img_tag.py,sha256=c4uE-bL9r0o40o7lSYsQIaVZNFoZJQoXCtqX2aLHGzQ,495
haruka_parser/table_processing/tags/list_tag.py,sha256=z5KKkKfHvVihR-UFnG3K-qy--hxDoxF_BbhvQXncmQo,1253
haruka_parser/table_processing/tags/table.py,sha256=NcA4oajTTFSfZJa0TdB-wGn1gyYK4wYxud7nPbSh6n4,6924
haruka_parser/table_processing/tags/table_tag.py,sha256=lYgN9_JhyKl2aCWyCtiXo8wp_R8D6N-pB-VSDfENcLM,1884
haruka_parser/tokenizer/__init__.py,sha256=9nnAOvIUKOkL_xyr-zE8l9gkkky-s_fV63v_cPHkaE0,32
haruka_parser/tokenizer/hash.py,sha256=Q5ZAiT2lJ6nydXvBx230-quj3Wdhb3SdYMxOKVaP-pE,2992
haruka_parser/tools/extract-hljs-languages.js,sha256=Kgh-vdzCHyAhSceg99cs8bACgLBGBID5d6_3nBw6DXI,733
haruka_parser/tools/hljs.py,sha256=f4jR4QsobnjcUpHhBIZDUajkTBA-L7qgpHA9tKpRDvg,3293
haruka_parser/trafilatura/.coveragerc,sha256=5fI-h5ybAji6oaMy4lgdVTPsFzcvdnpxE9LCPwlgKIE,236
haruka_parser/trafilatura/.readthedocs.yaml,sha256=ZY826LAonDh8px_fk-70SCGhSNfDdWW9z9qLpYgZzDo,1030
haruka_parser/trafilatura/CITATION.cff,sha256=wPAShWh3SOH8cqPbvqUBDWoqxJyYequyAP28vSiCC1U,796
haruka_parser/trafilatura/CONTRIBUTING.md,sha256=hT0XCPWFcqumq9rmiz3Zvv3k4HdrkRTLcDd_wf6AznE,2036
haruka_parser/trafilatura/HISTORY.md,sha256=8Sul9SbFBw8eZOO38YKZf4MPM6HqrS0HoU__Nr3aj7U,19358
haruka_parser/trafilatura/LICENSE,sha256=psuoW8kuDP96RQsdhzwOqi6fyWv0ct8CR6Jr7He_P_k,10173
haruka_parser/trafilatura/MANIFEST.in,sha256=qvdwMPoPMCW1mni0yBed1-Zj8FX6qtz9ZNoU8E7dOto,353
haruka_parser/trafilatura/README.md,sha256=C-FNg5V9OkgV2jMUEo_afQtyOTFjFzXB7hBPBzgObPo,9634
haruka_parser/trafilatura/compose.yml,sha256=nXp2TBDWQc5c7easGkCXjkc9DYRrmqozNXhGmyDD8K4,318
haruka_parser/trafilatura/pyproject.toml,sha256=DcdGQPRb1hE215GkxELnscD5-A1XoJ75ymtWo2Z8pl0,3584
haruka_parser/trafilatura/trafilatura/__init__.py,sha256=F2xBHUYjTIaT4tYfi1H2A63jPFTA3nkgGRCaRdZiWVs,808
haruka_parser/trafilatura/trafilatura/baseline.py,sha256=6vEFWkaiZ8YCq8cICfOZuJMC7s-ndA1BFYAoKgZrP8Q,4029
haruka_parser/trafilatura/trafilatura/cli.py,sha256=pX7EYYt0TZCDBosbqdo3ufq786hSTfAMoOR0GS4OA_k,10341
haruka_parser/trafilatura/trafilatura/cli_utils.py,sha256=U5SVH7m7CFNW2mXu3gEbX5pPBMNqXHbgtbyHnADu3gk,17590
haruka_parser/trafilatura/trafilatura/core.py,sha256=N5j5io5eo6NOnHTDNfwTgWVz8bkxqSBs3DmvOVYDXXo,24694
haruka_parser/trafilatura/trafilatura/deduplication.py,sha256=-kOh3vzvJXzey91DbowsNYlYPO13V7W75H8FffrAEGg,10632
haruka_parser/trafilatura/trafilatura/downloads.py,sha256=vu05IM8d0VABnNAG9TM5YgOYSSu13ZNWDKmSio-ZwF0,17281
haruka_parser/trafilatura/trafilatura/external.py,sha256=lOYPqNdycFA5u8_5qAqOY9lYRcoll5osbmlmQ-5YE5k,7631
haruka_parser/trafilatura/trafilatura/feeds.py,sha256=Vr6miPHazXr30B4HL4P47E2laLJ1SbYv9aOTYhM4908,9697
haruka_parser/trafilatura/trafilatura/htmlprocessing.py,sha256=KaJEpjJLiQD1QWp1qJfB8TgMjfr_9sDZBGyWXcuVjgs,15088
haruka_parser/trafilatura/trafilatura/json_metadata.py,sha256=m3pQVaXwMgJsIJDNAnvlSLydJgGgivDRAMrspuC4d9s,13020
haruka_parser/trafilatura/trafilatura/main_extractor.py,sha256=r50BL6STsn8lODZG5E6va-QKt_dv2ysSNO5PksMRZPA,30773
haruka_parser/trafilatura/trafilatura/meta.py,sha256=vDQ3xUBbwdJ4rWiURme4WzVlSFJRTezXzoBngRi4qCg,931
haruka_parser/trafilatura/trafilatura/metadata.py,sha256=XPYK49Y7Rk2Klo2Tu5NDWmu-4mtr08K_sPdkcon-vKs,19110
haruka_parser/trafilatura/trafilatura/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
haruka_parser/trafilatura/trafilatura/readability_lxml.py,sha256=crNfDFUNOMM3u820B5hqtPVcjIqw8wdiY3SC3z1q6Cw,19294
haruka_parser/trafilatura/trafilatura/settings.cfg,sha256=kTF3BW5g9gxB1t0rHhnDgKHJ_z-GmcVqkjK7OVXnRZ8,830
haruka_parser/trafilatura/trafilatura/settings.py,sha256=jOedBu3r4-9LGdYu6DdNOwU8cZD4wtzcfJU9zmCXTz0,12618
haruka_parser/trafilatura/trafilatura/sitemaps.py,sha256=XWKF-bw3BsAtw6HziQXrdmfG8ZzgizgrpSgSjA7lGGQ,9841
haruka_parser/trafilatura/trafilatura/spider.py,sha256=RGDUUGZuLwX4QVojBftB9-3_mQzCNKM4fvJD3Da6cKw,12132
haruka_parser/trafilatura/trafilatura/utils.py,sha256=wwN0CjUx7QYfGhR08y1msLH5BHvwZu9p4tZfenW4pIo,19863
haruka_parser/trafilatura/trafilatura/xml.py,sha256=8o-N2h60sYoqIz5LkLMLLoh2izNfHylCqfaz9beysX4,24812
haruka_parser/trafilatura/trafilatura/xpaths.py,sha256=x2FxeB3wyn-G6HijbK-j0mDNjbupbXkBuW_woSLsIFg,15194
haruka_parser/trafilatura/trafilatura/data/tei_corpus.dtd,sha256=UB5xeOqR0n2uXY6itoSZlSsOltIjra1UM8pJL_jXHZc,196033
haruka_parser/v2/README.md,sha256=CRSYsK-se0d1nJRmOwgaSZBaZgbmVzVucmgXlAUndqs,149
haruka_parser/v2/config.py,sha256=q2WUA0_cT3phdjsloRXiIw880L999VaGRSQpO40w0f0,2089
haruka_parser/v2/manager.py,sha256=GBW0qsiLPzus2-7Nri7ECDFwJicXn4UUDNnwMC3EMnY,8178
haruka_parser/v2/doms/base_dom.py,sha256=NT8LCUQJKU9emrOPByMQkSqKJz7t8Q2fe9T0xA8lx5g,483
haruka_parser/v2/doms/code_dom.py,sha256=2dz2A9ib7r_WkSlmQJsL0mGwTIjncup2LM0-80qVd0Q,3635
haruka_parser/v2/doms/link_dom.py,sha256=rfmRTYoVia4EQJlWZxUz7IOgY6VW6k5TzoHPVQYIdL0,5420
haruka_parser/v2/doms/math_dom.py,sha256=5c1QrVypx_aEHAb_QSTtZRQmCdMEXcsoXQA1fDn7h6E,26198
haruka_parser/v2/doms/media_dom.py,sha256=D24JmIjePS5_AW0Zfik-LxpMsZU3OWpakAGcy9BMNNg,3858
haruka_parser/v2/doms/normalize_dom.py,sha256=0wKaNDsiRpyT2GGdEizsRfByRgy-qkGju_15mYSr7fM,1007
haruka_parser/v2/doms/table_dom.py,sha256=H6cARo_Pmnz8STnL4-8-Q6nKGDPgcpNf0NPw9xhIVW8,7592
haruka_parser/v2/doms/turndown_dom.py,sha256=-V9yzMt8A_jU6dsC_I5Wu0Pg9Dx6jGX3Eni_UzrXdHY,20119
haruka_parser/v2/doms/useless_dom.py,sha256=kZLcqt2i0MYe7MC2lpvxyPowf8Jjlvz7uTLr6oZwfD0,3716
haruka_parser/v2/extractors/auto_extractor.py,sha256=WMprSUYc3bXNGo59tiW9UbGI04cxwi8pYmfktBBpkzs,8489
haruka_parser/v2/extractors/base_extractor.py,sha256=tMXL5392_lOj8S_5gXs9k3E6MCqTjKZa6pfA_uB4Odk,8269
haruka_parser/v2/extractors/cnki_extractor.py,sha256=2_1N10kzJIJqE_828T0T4GKnXcFL5SsNVfjlaXK2_04,1112
haruka_parser/v2/extractors/patch_extractor.py,sha256=ISrOdXq9Pci86MjFLbcMg6Pefr6AfnjjLbUDxzXSkCE,2058
haruka_parser/v2/extractors/time_extractor.py,sha256=SworLIFohRtUo9dtUxnOEWLctfBnzGkYTJJTBAFdgsQ,8440
haruka_parser/v2/extractors/title_extractor.py,sha256=E2CAw0iKZX9f6v8uayus1GCoWdR1BHitWmjw8K0aYEs,4455
haruka_parser/v2/formatters/ftfy.py,sha256=8BG9oKs9iWHIzFKulfHXYlCJ3ok-TYxZRX9Z42LmHjc,2537
haruka_parser/v2/formatters/justext.py,sha256=ZWj6YW1gHuBn9N5W6SFPUr2YbXipLld59SanPT5DNlc,4186
haruka_parser/v2/utils/decode_html.py,sha256=_TrX2RGN7n20UYUDFwIP5z5kMmbjfNG4wksgQHCm0oQ,4613
haruka_parser/v2/utils/lxml.py,sha256=XU98OKIYr0Ofu6LhY24vMqCUaM3Fr1_bmtEQ5xzpZ9w,6132
haruka_parser/v2/utils/sandbox.py,sha256=8PxasazkU1Wi9MeAWu2ieT0vzbFAbGDOzZK6SaCGCxk,3589
haruka_parser/v2/utils/tldextract.py,sha256=NJ1TT3D_O_tm0JljrjbvNo5bFE0KMv4-bbJ7_lcCi3M,28080
haruka_parser/v2/utils/tokens.py,sha256=FKpMR8SfMsbFilP2J2NEiLKGX3nagJUxM3mo0Q4exGU,3174
haruka_parser-1.1.1.dist-info/METADATA,sha256=CowiNSQDn2FEAqxS3q64nMGtaioQ_ZNVvcBG9-XARMQ,2762
haruka_parser-1.1.1.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
haruka_parser-1.1.1.dist-info/top_level.txt,sha256=0l3erGy0TeyrK1UpaKAJ0Ta4ewMvOxsK8150kDOw5C8,14
haruka_parser-1.1.1.dist-info/RECORD,,
