python - bs4提取XML/HTML中某个标签下的属性
一个例子就让你看明白。看完记得给博主点个赞噢。
我们要提取的xml原始文档来自以下网址：
https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/index.xml
先定义需要解析的文本：
【code - 1】：
xml="""<?xml version="1.0"?> <?xml-stylesheet href="index.xsl" type="text/xsl"?> <nltk_data> <packages> <package checksum="721ecf418efbfefb183d0559a7ef9f2d" id="perluniprops" license="" name="perluniprops: Index of Unicode Version 7.0.0 character properties in Perl" size="100266" subdir="misc" unzip="1" unzipped_size="136038" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/misc/perluniprops.zip" webpage="http://perldoc.perl.org/perluniprops.html" /> <package checksum="e5836f76779020b225ad6114372b954a" id="mwa_ppdb" license="Creative Commons Attribution 3.0 Unported (CC-BY)" name="The monolingual word aligner (Sultan et al. 2015) subset of the Paraphrase Database." size="1594711" subdir="misc" unzip="1" unzipped_size="3657054" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/misc/mwa_ppdb.zip" webpage="http://www.cis.upenn.edu/~ccb/ppdb/" /> <package author="Jan Strunk" checksum="398bbed6dd3ebb0752fe0735d1c418fe" id="punkt" languages="Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Italian, Norwegian, Polish, Portuguese, Russian, Slovene, Spanish, Swedish, Turkish" name="Punkt Tokenizer Models" size="13707633" subdir="tokenizers" unzip="1" unzipped_size="36797157" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/tokenizers/punkt.zip" /> <package author="Viviane Moreira Orengo (vmorengo@inf.ufrgs.br) and Christian Huyck" checksum="648798996224694251834699fa6e55f7" id="rslp" languages="Portuguese" name="RSLP Stemmer (Removedor de Sufixos da Lingua Portuguesa)" size="3805" subdir="stemmers" unzip="1" unzipped_size="7269" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/stemmers/rslp.zip" /> <package checksum="6af70bbc602aecd18aa0b9cfa7be2aa1" id="porter_test" name="Porter Stemmer Test Files" size="200510" subdir="stemmers" unzip="1" unzipped_size="680060" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/stemmers/porter_test.zip" /> <package checksum="cba1cf17b887789e6df5f2c87c6e56fb" id="snowball_data" languages="Danish, Dutch, English, Finnish, French, German, Hungarian, Italian, Norwegian, Portuguese, Romanian, Russian, Spanish, Swedish, Turkish" name="Snowball Data" size="6785405" subdir="stemmers" unzip="0" unzipped_size="36360836" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/stemmers/snowball_data.zip" webpage="https://github.com/snowballstem/snowball-data" /> <package checksum="d577c2cd0fdae148b36d046b14eb48e6" id="maxent_ne_chunker" languages="English" name="ACE Named Entity Chunker (Maximum entropy)" size="13404747" subdir="chunkers" unzip="1" unzipped_size="23604982" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/chunkers/maxent_ne_chunker.zip" /> <package checksum="715531d058ec253bd0683d0df23ec868" id="moses_sample" name="Moses Sample Models" size="10961490" subdir="models" unzip="1" unzipped_size="10985045" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/moses_sample.zip" webpage="http://www.statmt.org/moses/?n=Moses.SampleData" /> <package checksum="51d0c9c288b4f790bf255b5c9c3533ab" id="bllip_wsj_no_aux" name="BLLIP Parser: WSJ Model" size="24516205" subdir="models" unzip="1" unzipped_size="54298623" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/bllip_wsj_no_aux.zip" webpage="http://nlp.stanford.edu/~mcclosky/models/" /> <package checksum="d1d1a23377f9ab4c12d77c7a078318ac" id="word2vec_sample" name="Word2Vec Sample" size="49396025" subdir="models" unzip="1" unzipped_size="138432415" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/word2vec_sample.zip" webpage="https://code.google.com/p/word2vec/" /> <package checksum="2067e40eaf94ccb632007b91073aa433" id="wmt15_eval" name="Evaluation data from WMT15" size="383096" subdir="models" unzip="1" unzipped_size="1247631" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/wmt15_eval.zip" webpage="http://www.statmt.org/wmt15/" /> <package author="Kepa Sarasola" checksum="12f66b8e22beadd6ed202e95453465af" id="spanish_grammars" languages="Spanish" name="Grammars for Spanish" size="4047" subdir="grammars" unzip="1" unzipped_size="3980" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/spanish_grammars.zip" /> <package author="" checksum="c4a2a01345d1e61c8febd8d498c5d2d6" id="sample_grammars" languages="English" name="Sample Grammars" size="20293" subdir="grammars" unzip="1" unzipped_size="61718" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/sample_grammars.zip" /> <package checksum="135aa813bd721d59ae595d9d7f115dc8" contact="John A. Carroll" id="large_grammars" languages="English" license="See the individual grammar files" name="Large context-free and feature-based grammars for parser comparison" size="283747" subdir="grammars" unzip="1" unzipped_size="4115732" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/large_grammars.zip" webpage="http://www.informatics.sussex.ac.uk/research/groups/nlp/carroll/elsps.html" /> <package author="Ewan Klein" checksum="2e6bc2e5d678fc5d14e4c0747c69083e" id="book_grammars" languages="English" name="Grammars from NLTK Book" size="9103" subdir="grammars" unzip="1" unzipped_size="21179" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/book_grammars.zip" /> <package author="Kepa Sarasola" checksum="0e3518cb2aeb2600cb2841df7f035606" id="basque_grammars" languages="Spanish" name="Grammars for Basque" size="4704" subdir="grammars" unzip="1" unzipped_size="5550" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/basque_grammars.zip" /> <package checksum="e3b8a5353056073e164c5b06d0cc1fa7" id="maxent_treebank_pos_tagger" languages="English" name="Treebank Part of Speech Tagger (Maximum entropy)" size="10156853" subdir="taggers" unzip="1" unzipped_size="17961132" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/maxent_treebank_pos_tagger.zip" /> <package checksum="05c91d607ee1043181233365b3f76978" id="averaged_perceptron_tagger" languages="English" name="Averaged Perceptron Tagger" size="2526731" subdir="taggers" unzip="1" unzipped_size="6138625" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/averaged_perceptron_tagger.zip" /> <package checksum="f7051368e4aff6718f8b38c1362dfdb1" id="averaged_perceptron_tagger_ru" languages="Russian" name="Averaged Perceptron Tagger (Russian)" size="8628828" subdir="taggers" unzip="1" unzipped_size="23247411" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/averaged_perceptron_tagger_ru.zip" webpage="http://www.ruscorpora.ru/en/" /> <package checksum="137e73955092dd93345c8593c4691be9" id="universal_tagset" name="Mappings to the Universal Part-of-Speech Tagset" size="19095" subdir="taggers" unzip="1" unzipped_size="37147" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/universal_tagset.zip" /> <package author="C.J. Hutto and Eric Gilbert" checksum="8b3824e2c39b655dd225fb266c8bea53" id="vader_lexicon" license="MIT License" name="VADER Sentiment Lexicon" size="90486" subdir="sentiment" unzip="0" unzipped_size="434147" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/sentiment/vader_lexicon.zip" webpage="https://github.com/cjhutto/vaderSentiment" /> <package author="Dekang Lin" checksum="288cc15e4ed257c8598d6f7a30199db9" id="lin_thesaurus" license="Distributed with permission of Dekang Lin" name="Lin's Dependency Thesaurus" size="89154019" subdir="corpora" unzip="1" unzipped_size="210421609" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/lin_thesaurus.zip" webpage="http://webdocs.cs.ualberta.ca/~lindek/downloads.htm" /> <package author="Bo Pang and Lillian Lee" checksum="155de2b77c6834dd8eea7cbe88e93acb" copyright="Copyright (C) 2004 Bo Pang and Lillian Lee" id="movie_reviews" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Sentiment Polarity Dataset Version 2.0" size="4004848" subdir="corpora" unzip="1" unzipped_size="7790571" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/movie_reviews.zip" webpage="http://www.cs.cornell.edu/people/pabo/movie-review-data/" /> <package author="Andrew Ko, Carnegie Mellon University" checksum="8781ace4c0a181c5875cdbfc01e895fb" id="problem_reports" name="Problem Report Corpus" size="1032942" subdir="corpora" unzip="1" unzipped_size="3467763" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/problem_reports.zip" webpage="http://www.cs.cmu.edu/~marmalade/reports.html" /> <package author="Bing Liu" checksum="c4c7e61fb4d57a2f6c95317194da0f17" copyright="Copyright (C) 2008 Bing Liu" id="pros_cons" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Pros and Cons" size="746276" subdir="corpora" unzip="1" unzipped_size="2921218" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pros_cons.zip" webpage="http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#datasets" /> <package author="Nancy Ide" checksum="a03d3ae8c6c2a1707885066e4d62582a" copyright="Copyright (C) 2014 American National Corpus" id="masc_tagged" license="This data may be used for the purposes of linguistic education, research, and development, including commercial development." name="MASC Tagged Corpus" size="1602143" subdir="corpora" unzip="0" unzipped_size="4963879" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/masc_tagged.zip" webpage="http://www.anc.org/" /> <package author="Bo Pang and Lillian Lee" checksum="5cdc0cae7f558040d050c90eb2b72e97" copyright="Copyright (C) 2005 Bo Pang and Lillian Lee" id="sentence_polarity" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Sentence Polarity Dataset v1.0" size="490256" subdir="corpora" unzip="1" unzipped_size="1241127" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/sentence_polarity.zip" webpage="http://www.cs.cornell.edu/People/pabo/people/pabo/movie-review-data" /> <package checksum="6c7680030aae5c997b1370f832545c6a" id="webtext" name="Web Text Corpus" size="646297" subdir="corpora" unzip="1" unzipped_size="1726918" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/webtext.zip" /> <package author="Craig Martell (cmartell@nps.edu)" checksum="72d1b905ba2be48d711690b012856c79" id="nps_chat" license="This corpus is distributed solely for non-commercial, non-profit educational and research use. It is a derivative compilation work of multiple works whose copyrights are held by the respective original authors." name="NPS Chat" size="301366" subdir="corpora" unzip="1" unzipped_size="2578726" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/nps_chat.zip" webpage="http://faculty.nps.edu/cmartell/NPSChat.htm" /> <package checksum="29cbf1aa02ad8abc72dd955fe74f882c" id="city_database" name="City Database" note="A very small database of information about cities" size="1708" subdir="corpora" unzip="1" unzipped_size="4096" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/city_database.zip" /> <package author="Philipp Koehn, University of Edinburgh" checksum="7621d5675990b1decc012c823716ee76" id="europarl_raw" name="Sample European Parliament Proceedings Parallel Corpus" size="12594977" subdir="corpora" unzip="1" unzipped_size="41396100" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/europarl_raw.zip" webpage="http://www.statmt.org/europarl" /> <package checksum="d3be36b53ab201372f1cd63ffc75e9a9" copyright="Public Domain (not copyrighted)" id="biocreative_ppi" license="Public Domain" name="BioCreAtIvE (Critical Assessment of Information Extraction Systems in Biology)" size="223566" subdir="corpora" unzip="1" unzipped_size="1537086" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/biocreative_ppi.zip" webpage="http://www.mitre.org/public/biocreative/" /> <package author="Karin Kipper-Schuler" checksum="60efc5ed90ab8a18ef4a436e4c39ffbf" id="verbnet3" license="Distributed with permission of the author." name="VerbNet Lexicon, Version 3.3" size="482025" subdir="corpora" unzip="1" unzipped_size="3723345" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/verbnet3.zip" version="3.3" webpage="https://verbs.colorado.edu/verbnet/" /> <package checksum="e72135042dc48772acad309a6adbb6f0" id="pe08" license="Distributed with permission" name="Cross-Framework and Cross-Domain Parser Evaluation Shared Task" size="80735" subdir="corpora" unzip="1" unzipped_size="296619" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pe08.zip" version="Release 3 (20 April 2008)" webpage=" http://www-tsujii.is.s.u-tokyo.ac.jp/pe08-st/" /> <package checksum="d07b2ca7b5b351a24f4db8ae8fbc9e98" id="pil" license="Distributed with permission" name="The Patient Information Leaflet (PIL) Corpus" size="1510205" subdir="corpora" unzip="1" unzipped_size="4170899" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pil.zip" version="Version 2.0 (31 March 2006)" webpage="http://mcs.open.ac.uk/nlg/old_projects/pills/corpus/" /> <package author="Kevin Scannell" checksum="3cc831382dec41b8d9a06d93ef300352" copyright="Copyright (C) 2010 Kevin Scannell" id="crubadan" license="GPLv3" name="Crubadan Corpus" size="5288655" subdir="corpora" unzip="1" unzipped_size="11256183" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/crubadan.zip" webpage="http://borel.slu.edu/crubadan/" /> <package checksum="48c9c8605cd70b0230687557ee543633" copyright="public domain" id="gutenberg" license="public domain" name="Project Gutenberg Selections" size="4251829" subdir="corpora" unzip="1" unzipped_size="11802669" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/gutenberg.zip" webpage="http://gutenberg.net/" /> <package checksum="2397782c6e6f46c9657f85db8a5421f6" contact="Martha Palmer" id="propbank" license="Distributed with permission" name="Proposition Bank Corpus 1.0" size="5323498" subdir="corpora" unzip="0" unzipped_size="18831005" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/propbank.zip" webpage="http://verbs.colorado.edu/~mpalmer/projects/ace.html" /> <package author="Machado de Assis" checksum="d186f7d6715479a8bec48b8b8030858e" id="machado" license="Public Domain" name="Machado de Assis -- Obra Completa" size="6151774" subdir="corpora" unzip="0" unzipped_size="14855338" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/machado.zip" webpage="http://machado.mec.gov.br/" /> <package checksum="044f2d20c592b17a26ac0102111833c9" copyright="public domain" id="state_union" license="public domain" name="C-Span State of the Union Address Corpus" size="808757" subdir="corpora" unzip="1" unzipped_size="2073917" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/state_union.zip" webpage="http://www.c-span.org/executive/stateoftheunion.asp" /> <package checksum="02fc79b5adc0357bc1e14747246fd3c1" copyright="Copyright (C) 2015 Twitter, Inc" id="twitter_samples" license="Must be used subject to Twitter Developer Agreement (https://dev.twitter.com/overview/terms/agreement)" name="Twitter Samples" note="Sample of Tweets collected from the Twitter APIs, observing the 50k limit required by https://dev.twitter.com/overview/terms/policy#6._Be_a_Good_Partner_to_Twitter " size="16007673" subdir="corpora" unzip="1" unzipped_size="122350791" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/twitter_samples.zip" /> <package author="Rada Mihalcea (rada@cs.unt.edu)" checksum="46c095f0ab7090132567f87252af724f" id="semcor" license="You are granted permission to use, copy, modify and distribute this database for any purpose and without fee and royalty is hereby granted, provided that you agree to comply with the Princeton copyright notice and statements, including the disclaimer, and that the same appear on ALL copies of the database, including modifications that you make for internal use or for distribution. See semcor/README for more information." name="SemCor 3.0" size="4397021" subdir="corpora" unzip="0" unzipped_size="37425596" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/semcor.zip" webpage="http://www.cse.unt.edu/~rada/downloads.html#semcor" /> <package author="Mark Kantrowitz and Bill Ross" checksum="93844d7c995ad28f40528c08a3430175" copyright="Copyright (C) 1991 Mark Kantrowitz" id="names" license="You may use the lists of names for any purpose, so long as credit is given in any published work. You may also redistribute the list if you provide the recipients with a copy of this README file. The lists are not in the public domain (I retain the copyright on the lists) but are freely redistributable. If you have any additions to the lists of names, I would appreciate receiving them." name="Names Corpus, Version 1.3 (1994-03-29)" size="21326" subdir="corpora" unzip="1" unzipped_size="56572" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/names.zip" webpage="http://www-2.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/nlp/corpora/names/" /> <package checksum="7b633a1b7770279eab00bc1108769c67" copyright="Copyright (C) 1995 University of Pennsylvania" id="ptb" license="This is a stub for the full Penn Treebank Corpus version 3." name="Penn Treebank" size="6289" subdir="corpora" unzip="1" unzipped_size="63036" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ptb.zip" /> <package checksum="57afdc46230ea33208e4e277de24765b" contact="Adam Meyers" id="nombank.1.0" license="Distributed with permission" name="NomBank Corpus 1.0" size="6728397" subdir="corpora" unzip="0" unzipped_size="42315496" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/nombank.1.0.zip" webpage="http://nlp.cs.nyu.edu/meyers/NomBank.html" /> <package checksum="de5f1df09949f080e0f616f0bc55967d" id="floresta" license="Non-commercial use only" name="Portuguese Treebank" size="1882021" subdir="corpora" unzip="1" unzipped_size="16414136" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/floresta.zip" webpage="http://www.linguateca.pt/Floresta/" /> <package author="Reinhard Rapp" checksum="8e1e34e2f052d8188fd877b2c821b42d" id="comtrans" name="ComTrans Corpus Sample" size="11904518" subdir="corpora" unzip="0" unzipped_size="35387522" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/comtrans.zip" webpage="http://www.fask.uni-mainz.de/user/rapp/comtrans/" /> <package checksum="992f8a3647f333e28a9958eba4bd67c7" id="knbc" license="Freely re-distributable under the same license as the original KNB Corpus." name="KNB Corpus (Annotated blog corpus)" size="8760788" subdir="corpora" unzip="0" unzipped_size="23601139" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/knbc.zip" webpage="http://lilyx.net/pages/nltkjapanesecorpus.html" /> <package checksum="cf216ae5b37cca24866909f8594c5395" id="mac_morpho" license="Distributed with permission of Núcleo Interinstitucional de Lingüística Computacional (NILC), Universidade de São Paulo (USP) in São Carlos, Universidade Federal de São Carlos (UFSCar), Universidade Estadual Paulista (UNESP) of Araraquara." name="MAC-MORPHO: Brazilian Portuguese news text with part-of-speech tags" size="3013904" subdir="corpora" unzip="1" unzipped_size="10941402" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/mac_morpho.zip" webpage="http://www.nilc.icmc.usp.br/lacioweb/" /> <package checksum="6612ccb71f327e85780dc7813dee40f6" id="swadesh" license="GNU Free Documentation License" name="Swadesh Wordlists" size="22828" subdir="corpora" unzip="1" unzipped_size="39998" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/swadesh.zip" webpage="http://en.wiktionary.org/wiki/Appendix:Swadesh_list" /> <package checksum="ca21663daa326a3bb53001c3d82e62d6" id="rte" name="PASCAL RTE Challenges 1, 2, and 3" size="386303" subdir="corpora" unzip="1" unzipped_size="1279930" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/rte.zip" webpage="http://www.pascal-network.org/Challenges/RTE/" /> <package checksum="26657c1b8b5f5afdc3d5d754393a9216" id="toolbox" name="Toolbox Sample Files" size="250616" subdir="corpora" unzip="1" unzipped_size="829593" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/toolbox.zip" /> <package checksum="96e30423d6887fad17fc44f2f30d920d" id="jeita" license="Freely re-distributable under the same license as the original JEITA corpus. Each document retains its own license from Aozora bunko and Project Sugita Genpaku." name="JEITA Public Morphologically Tagged Corpus (in ChaSen format)" size="16531215" subdir="corpora" unzip="0" unzipped_size="134170650" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/jeita.zip" webpage="http://lilyx.net/pages/nltkjapanesecorpus.html" /> <package author="Bing Liu" checksum="c13be66052027a4605ca456d7cda0917" copyright="Copyright (C) 2004 Bing Liu" id="product_reviews_1" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Product Reviews (5 Products)" size="141287" subdir="corpora" unzip="1" unzipped_size="396548" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/product_reviews_1.zip" webpage="http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#datasets" /> <package author="Francis Bond" checksum="8e2adf0627365f0c51a05807737a5e5c" copyright="Please consult the copyright statements of the individual Wordnets" id="omw" license="Please consult the LICENSE files included with the individual Wordnets. Note that all permit redistribution." name="Open Multilingual Wordnet" size="12110409" subdir="corpora" unzip="1" unzipped_size="50269427" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/omw.zip" webpage="http://compling.hss.ntu.edu.sg/omw/" /> <package author="Stefano Baccianella, Andrea Esuli, and Fabrizio Sebastiani" checksum="5043f00829b7db4dd5f21507e092b76a" copyright="Copyright (C) 2013 SentiWordNet Project" id="sentiwordnet" license="Creative Commons Attribution ShareAlike 3.0 Unported license" name="SentiWordNet" size="4686546" subdir="corpora" unzip="1" unzipped_size="13591402" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/sentiwordnet.zip" webpage="http://sentiwordnet.isti.cnr.it/" /> <package author="Bing Liu" checksum="522134e8b91086473299c3800c4adbae" copyright="Copyright (C) 2007 Bing Liu" id="product_reviews_2" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Product Reviews (9 Products)" size="170698" subdir="corpora" unzip="1" unzipped_size="438549" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/product_reviews_2.zip" webpage="http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#datasets" /> <package author="Australian Broadcasting Commission" checksum="ffb36b67ff24cbf7daaf171c897eb904" id="abc" name="Australian Broadcasting Commission 2006" size="1487851" subdir="corpora" unzip="1" unzipped_size="4054966" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/abc.zip" webpage="http://www.abc.net.au/" /> <package checksum="e604482d2dc8dd2580af7d97c1bf0a80" copyright="public domain" id="udhr2" license="public domain" name="Universal Declaration of Human Rights Corpus (Unicode Version)" size="1653975" subdir="corpora" unzip="1" unzipped_size="5677920" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/udhr2.zip" webpage="http://unicode.org/udhr/" /> <package checksum="bfc6a33c62ddc2ec24b02701a2f364ff" contact="Ted Pedersen (tpederse@umn.edu)" id="senseval" license="Distributed with permission." name="SENSEVAL 2 Corpus: Sense Tagged Text" size="2151350" subdir="corpora" unzip="1" unzipped_size="16463075" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/senseval.zip" webpage="http://www.senseval.org/" /> <package checksum="8594d9d5422e01d993dfbbc3f38d3ae5" copyright="public domain" id="words" license="public domain" name="Word Lists" size="757777" subdir="corpora" unzip="1" unzipped_size="2498552" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/words.zip" webpage="http://en.wikipedia.org/wiki/Words_(Unix)" /> <package author="Collin F. Baker" checksum="cf68365950b2f048bcb48619de81f50a" id="framenet_v15" license="May be used for non-commercial purposes." name="FrameNet 1.5" size="69337891" subdir="corpora" unzip="1" unzipped_size="579133737" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/framenet_v15.zip" webpage="http://framenet.icsi.berkeley.edu" /> <package checksum="d46699450dd2287f5c115d8c1a0819f1" id="unicode_samples" name="Unicode Samples" note="A very small corpus used to demonstrate unicode encoding in chapter 10 of the book" size="1212" subdir="corpora" unzip="1" unzipped_size="643" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/unicode_samples.zip" /> <package checksum="68a8716e0233ad9c0ed0947952e4eb3e" id="kimmo" name="PC-KIMMO Data Files" size="186958" subdir="corpora" unzip="1" unzipped_size="814609" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/kimmo.zip" webpage="http://www.sil.org/pckimmo/" /> <package author="Collin F. Baker" checksum="aaef1cfdcf37000cf2a5c562407fbddb" id="framenet_v17" license="Creative Commons Attribution 3.0 Unported License" name="FrameNet 1.7" size="99207152" subdir="corpora" unzip="1" unzipped_size="855026962" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/framenet_v17.zip" webpage="http://framenet.icsi.berkeley.edu" /> <package author="David Warren and Fernando Pereira" checksum="6832873fe92996846ac5bb21c5d84eb8" copyright="Copyright (C) 1982 David Warren and Fernando Pereira" id="chat80" license="This program may be used, copied, altered or included in other programs only for academic purposes and provided that the authorship of the initial program is aknowledged. Use for commercial purposes without the previous written agreement of the authors is forbidden." name="Chat-80 Data Files" size="19209" subdir="corpora" unzip="1" unzipped_size="63817" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/chat80.zip" webpage="http://www.cis.upenn.edu/~pereira/oldies.html" /> <package author="Xin Li and Dan Roth, UIUC" checksum="afd4145ac31cb8d7db715974b9b8b57a" id="qc" name="Experimental Data for Question Classification" size="125456" subdir="corpora" unzip="1" unzipped_size="361090" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/qc.zip" webpage="http://l2r.cs.uiuc.edu/~cogcomp/Data/QA/QC/" /> <package checksum="bbb9abb8749666f92b855cba3d678708" copyright="public domain" id="inaugural" license="public domain" name="C-Span Inaugural Address Corpus" size="329806" subdir="corpora" unzip="1" unzipped_size="793473" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/inaugural.zip" /> <package checksum="b3f38606f626e54c6f060548546f71f0" copyright="WordNet 3.0 Copyright 2006 by Princeton University. All rights reserved." id="wordnet" license="Permission to use, copy, modify and distribute this software and database and its documentation for any purpose and without fee or royalty is hereby granted, provided that you agree to comply with the following copyright notice and statements, including the disclaimer, and that the same appear on ALL copies of the software, database and documentation, including modifications that you make for internal use or for distribution.... [see webpage for full license]" name="WordNet" size="10775600" subdir="corpora" unzip="1" unzipped_size="36353991" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/wordnet.zip" version="3.0" webpage="http://wordnet.princeton.edu/" /> <package checksum="884694b9055d1caee8a0ca3aa3b2c7f7" id="stopwords" name="Stopwords Corpus" size="23047" subdir="corpora" unzip="1" unzipped_size="54414" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/stopwords.zip" webpage="ftp://ftp.cs.cornell.edu/pub/smart/english.stop and http://snowball.tartarus.org/ and others" /> <package author="Karin Kipper-Schuler" checksum="427dac60e4a94ae910248ccd9986a22a" id="verbnet" license="Distributed with permission of the author." name="VerbNet Lexicon, Version 2.1" size="323661" subdir="corpora" unzip="1" unzipped_size="2474526" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/verbnet.zip" version="2.1" webpage="https://verbs.colorado.edu/verbnet/" /> <package checksum="2332b32a7d83d657092ba4667c2c84c3" copyright="public domain" id="shakespeare" license="public domain" name="Shakespeare XML Corpus Sample" sample="True" size="475458" subdir="corpora" unzip="1" unzipped_size="1727210" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/shakespeare.zip" webpage="http://www.andrew.cmu.edu/user/akj/shakespeare/" /> <package available="False" checksum="6582cd98ca26c35d9c4eaaa4350ce8f3" id="ycoe" name="York-Toronto-Helsinki Parsed Corpus of Old English Prose" size="477" subdir="corpora" unzip="1" unzipped_size="277" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ycoe.zip" webpage="http://www.ota.ahds.ac.uk/" /> <package checksum="34157f569624bc8d642ef8da5722b14a" id="ieer" name="NIST IE-ER DATA SAMPLE" size="166156" subdir="corpora" unzip="1" unzipped_size="541349" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ieer.zip" webpage="http://www.itl.nist.gov/iad/894.01/tests/ie-er/er_99/er_99.htm" /> <package checksum="e91ac59ec6e98e3b297e2d2eab83084d" id="cess_cat" license="If you use these corpora for research, please cite thusly: CESS-Cat project (M. Antonia Martí, MarionaTaulé, Lluís Márquez, Manuel Bertran (2007) ?CESS-ECE: A Multilingual and Multilevel Annotated Corpus? in http://www.lsi.upc.edu/~mbertran/cess-ece/publications)." name="CESS-CAT Treebank" size="5396688" subdir="corpora" unzip="1" unzipped_size="33720460" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/cess_cat.zip" webpage="http://clic.ub.edu/cessece/" /> <package checksum="878df010a9f2c2d0a6546a8365f10595" id="switchboard" license="Permission is granted for use of this material in accordance with the Open Content License [http://opencontent.org/opl.shtml]. This corpus contains transcripts and annotations for 36 calls from the Switchboard Corpus [http://www.ldc.upenn.edu/Catalog/LDC93S7.html]." name="Switchboard Corpus Sample" sample="True" size="791161" subdir="corpora" unzip="1" unzipped_size="2541179" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/switchboard.zip" /> <package author="Nitin Jindal and Bing Liu" checksum="df2d005f455afb760fa37d7f565400f1" copyright="Copyright (C) 2006 Nitin Jindal and Bing Liu" id="comparative_sentences" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Comparative Sentence Dataset" size="279121" subdir="corpora" unzip="1" unzipped_size="774200" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/comparative_sentences.zip" webpage="http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#datasets" /> <package author="Bo Pang and Lillian Lee" checksum="a81a44513903ba6bb86f85aeff149561" copyright="Copyright (C) 2004 Bo Pang and Lillian Lee" id="subjectivity" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Subjectivity Dataset v1.0" size="521628" subdir="corpora" unzip="1" unzipped_size="1303352" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/subjectivity.zip" webpage=" http://www.cs.cornell.edu/People/pabo/people/pabo/movie-review-data" /> <package checksum="745b3a90feb25c95fc805ebbd1ef5258" copyright="public domain" id="udhr" license="public domain" name="Universal Declaration of Human Rights Corpus" size="1170177" subdir="corpora" unzip="1" unzipped_size="3261577" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/udhr.zip" webpage="http://www.un.org/Overview/rights.html" /> <package author="I. Kurcz, A. Lewicki, J. Sambor, K. Szafran, J. Woronczak" checksum="bcbdcf0fc2420fac238ca17dc7bfe423" id="pl196x" license="GNU General Public License" name="Polish language of the XX century sixties" size="7051453" subdir="corpora" unzip="1" unzipped_size="58299303" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pl196x.zip" webpage="http://www.mimuw.edu.pl/polszczyzna/pl196x/index_en.htm" /> <package author="Cathy Bow, University of Melbourne" checksum="745ee9036c5ca3226be24c97515f5707" id="paradigms" license="Distributed with the permission of the author" name="Paradigm Corpus" size="24902" subdir="corpora" unzip="1" unzipped_size="361186" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/paradigms.zip" /> <package checksum="1dd15c714a2be985c482a13d90e9caa4" id="gazetteers" license="GNU Free Documentation License; or public domain (depending on the file)" name="Gazeteer Lists" size="8265" subdir="corpora" unzip="1" unzipped_size="12711" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/gazetteers.zip" /> <package checksum="34c047c4749a811287f2c652104d7849" id="timit" license="This corpus sample is Copyright 1993 Linguistic Data Consortium, and is distributed under the terms of the Creative Commons Attribution, Non-Commercial, ShareAlike license. http://creativecommons.org/" name="TIMIT Corpus Sample" sample="True" size="22251869" subdir="corpora" unzip="1" unzipped_size="31932925" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/timit.zip" webpage="http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC93S1" /> <package checksum="78c24a97940c2504d0ad35dd3f8a560b" copyright="Copyright (C) 1995 University of Pennsylvania" id="treebank" license="This is a 10% fragment of Penn Treebank, (C) LDC 1995. It is made available under fair use for the purposes of illustrating NLTK tools for tokenizing, tagging, chunking and parsing. This data is for non-commercial use only." name="Penn Treebank Sample" sample="True" size="1740034" subdir="corpora" unzip="1" unzipped_size="5963497" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/treebank.zip" /> <package checksum="3e314e26c852c5796488244ffef2ac91" id="sinica_treebank" license="Distributed with the Natural Language Toolkit under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike License [http://creativecommons.org/licenses/by-nc-sa/2.5/]." name="Sinica Treebank Corpus Sample" sample="True" size="899237" subdir="corpora" unzip="1" unzipped_size="3293082" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/sinica_treebank.zip" webpage="http://rocling.iis.sinica.edu.tw/CKIP/engversion/treebank.htm" /> <package author="Bing Liu" checksum="43a521f055063e001845b9d484a50173" copyright="Copyright (C) 2011 Bing Liu" id="opinion_lexicon" license="Creative Commons Attribution 4.0 International" licenseurl="http://creativecommons.org/licenses/by/4.0/" name="Opinion Lexicon" size="24947" subdir="corpora" unzip="1" unzipped_size="67865" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/opinion_lexicon.zip" webpage="http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#datasets" /> <package author="Adwait Ratnaparkhi" checksum="cce212b7ace8e64722ba2f41f802a5d0" copyright="(C) 1994 Adwait Ratnaparkhi" id="ppattach" license="Distributed with the permission of the author." name="Prepositional Phrase Attachment Corpus" size="781714" subdir="corpora" unzip="1" unzipped_size="3113650" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ppattach.zip" webpage="ftp://ftp.cis.upenn.edu/pub/adwait/PPattachData/" /> <package checksum="631e959acaa42eea718daf04c5cdfa76" copyright="Copyright (C) 1995 University of Pennsylvania" id="dependency_treebank" license="This is a 10% fragment of Penn Treebank, (C) LDC 1995, which has been dependency parsed. It is made available under fair use for the purposes of illustrating NLTK tools for tokenizing, tagging, chunking and parsing. This data is for non-commercial use only." name="Dependency Parsed Treebank" sample="True" size="457429" subdir="corpora" unzip="1" unzipped_size="1069540" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/dependency_treebank.zip" /> <package checksum="c2acb24d5cccf8035e0fe8d29f440a68" id="reuters" license="The copyright for the text of newswire articles and Reuters annotations in the Reuters-21578 collection resides with Reuters Ltd. Reuters Ltd. and Carnegie Group, Inc. have agreed to allow the free distribution of this data *for research purposes only*. If you publish results based on this data set, please acknowledge its use, refer to the data set by the name 'Reuters-21578, Distribution 1.0', and inform your readers of the current location of the data set." name="The Reuters-21578 benchmark corpus, ApteMod version" size="6378691" subdir="corpora" unzip="0" unzipped_size="9073648" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/reuters.zip" webpage="http://kdd.ics.uci.edu/databases/reuters21578/reuters21578.html" /> <package checksum="2a76432753c01fe179684e0ae3a4d023" copyright="public domain" id="genesis" license="public domain" name="Genesis Corpus" size="473239" subdir="corpora" unzip="1" unzipped_size="1426122" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/genesis.zip" /> <package checksum="684432d4f6384b8f0bd19fee5dc15925" id="cess_esp" license="If you use these corpora for research, please cite thusly: CESS-Cat project (M. Antonia Martí, MarionaTaulé, Lluís Márquez, Manuel Bertran (2007) ?CESS-ECE: A Multilingual and Multilevel Annotated Corpus? in http://www.lsi.upc.edu/~mbertran/cess-ece/publications)." name="CESS-ESP Treebank" size="2220392" subdir="corpora" unzip="1" unzipped_size="13233272" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/cess_esp.zip" webpage="http://clic.ub.edu/cessece/" /> <package checksum="b9015928e35c41f0695525289df5208f" contact="Kepa Sarasola" copyright="Copyright (C) 2007 The University of the Basque Country" id="conll2007" license="Creative Commons Attribution-NonCommercial-NoDerivativeWorks license" name="Dependency Treebanks from CoNLL 2007 (Catalan and Basque Subset)" size="1242958" subdir="corpora" unzip="0" unzipped_size="6399295" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/conll2007.zip" webpage="http://nextens.uvt.nl/depparse-wiki/DataDownload" /> <package checksum="5e7d700390745114cd3a52160d6f2eac" id="nonbreaking_prefixes" license="Gnu LGPL" name="Non-Breaking Prefixes (Moses Decoder)" size="25437" subdir="corpora" unzip="1" unzipped_size="43361" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/nonbreaking_prefixes.zip" webpage="https://github.com/moses-smt/mosesdecoder/tree/master/scripts/share/nonbreaking_prefixes" /> <package checksum="6f9c042774b96366c93fd0f9a9adb697" id="dolch" name="Dolch Word List" size="2116" subdir="corpora" unzip="1" unzipped_size="1917" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/dolch.zip" webpage="https://en.wikipedia.org/wiki/Dolch_word_list" /> <package author="Sofia Gustafson-Capkova, Yvonne Samuelsson, and Martin Volk" checksum="8743ff232d76aaf2ff8a10523503a659" id="smultron" name="SMULTRON Corpus Sample" size="166207" subdir="corpora" unzip="1" unzipped_size="1677647" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/smultron.zip" webpage="http://www.ling.su.se/DaLi/research/smultron/index.htm" /> <package checksum="ae529a1c5f13d6074f5b0d68d8edb537" contact="Gertjan van Noord" id="alpino" license="Distributed with permission of Gertjan van Noord" name="Alpino Dutch Treebank" size="2797255" subdir="corpora" unzip="1" unzipped_size="21604821" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/alpino.zip" webpage="http://www.let.rug.nl/~vannoord/trees/" /> <package checksum="25f0185b31693fa11ea898e4feda528c" id="wordnet_ic" name="WordNet-InfoContent" size="12056682" subdir="corpora" unzip="1" unzipped_size="34220359" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/wordnet_ic.zip" version="3.0" webpage="http://wn-similarity.sourceforge.net" /> <package author="W. N. Francis and H. Kucera" checksum="a0a8630959d3d937873b1265b0a05497" id="brown" license="May be used for non-commercial purposes." name="Brown Corpus" size="3314357" subdir="corpora" unzip="1" unzipped_size="10117565" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/brown.zip" webpage="http://www.hit.uib.no/icame/brown/bcm.html" /> <package author="Jonathan Pool (editor)" checksum="66dd080f09ac17db3d31bb4d667d0794" id="panlex_swadesh" license="CC0 1.0 Universal" name="PanLex Swadesh Corpora" size="2861668" subdir="corpora" unzip="0" unzipped_size="4418150" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/panlex_swadesh.zip" webpage="http://panlex.org/" /> <package checksum="9529b285edd5fe47271da69df1052301" contact="Erik Tjong Kim Sang (erikt@uia.ua.ac.be)" id="conll2000" name="CONLL 2000 Chunking Corpus" size="756607" subdir="corpora" unzip="1" unzipped_size="3495903" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/conll2000.zip" webpage="http://www.cnts.ua.ac.be/conll2000/chunking/" /> <package checksum="4acd3991768a727be019a8021fe376d2" id="universal_treebanks_v20" license="Creative Commons Attribution-NonCommercial-ShareAlike 3.0 United States" name="Universal Treebanks Version 2.0" size="25908853" subdir="corpora" unzip="0" unzipped_size="119113962" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/universal_treebanks_v20.zip" webpage="https://code.google.com/p/uni-dep-tb/" /> <package author="W. N. Francis and H. Kucera" checksum="3c7fe43ebf0a4c7ad3ebb63dab027e09" contact="Lou Burnard -- lou.burnard@oucs.ox.ac.uk" id="brown_tei" license="May be used for non-commercial purposes." name="Brown Corpus (TEI XML Version)" size="8737738" subdir="corpora" unzip="1" unzipped_size="56814689" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/brown_tei.zip" webpage="http://www.hit.uib.no/icame/brown/bcm.html" /> <package checksum="58f743ff818b983b89ef9302b509fc41" copyright="Copyright 1998 Carnegie Mellon University" id="cmudict" license="Use of this dictionary, for any research or commercial purpose, is completely unrestricted. If you use or redistribute this material, we would appreciate acknowlegement of its origin." name="The Carnegie Mellon Pronouncing Dictionary (0.6)" size="896069" subdir="corpora" unzip="1" unzipped_size="3824638" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/cmudict.zip" webpage="ftp://ftp.cs.cmu.edu/project/speech/dict/" /> <package author="Erjavec, Tomaž; Barbu, Ana-Maria; Derzhanski, Ivan; Dimitrova, Ludmila; Garabík, Radovan; Ide, Nancy; Kaalep, Heiki-Jaan; Kotsyba, Natalia; Krstev, Cvetana; Oravecz, Csaba; Petkevič, Vladimír; Priest-Dorman, Greg; QasemiZadeh, Behrang; Radziszewski, Adam; Simov, Kiril; Tufiş, Dan and Zdravkova, Katerina" checksum="27aa12b3546cb241df8699506ab15128" id="mte_teip5" license="Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)" name="MULTEXT-East 1984 annotated corpus 4.0" size="14800561" subdir="corpora" unzip="1" unzipped_size="122461442" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/mte_teip5.zip" webpage="https://www.clarin.si/repository/xmlui/handle/11356/1043" /> <package author="A Kumaran" checksum="599a684793935ecbcf8276133945037c" id="indian" license="Distributed with permission" name="Indian Language POS-Tagged Corpus" size="199187" subdir="corpora" unzip="1" unzipped_size="1091033" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/indian.zip" /> <package checksum="67bb4ca75fa81544d42a159524726e78" id="conll2002" name="CONLL 2002 Named Entity Recognition Corpus" size="1867449" subdir="corpora" unzip="1" unzipped_size="7785638" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/conll2002.zip" webpage="http://www.cnts.ua.ac.be/conll2002/ner/" /> <package author="UCREL, Lancaster University" checksum="e15834e0dd89b107925af6bb11a8eaa4" id="tagsets" languages="English" name="Help on Tagsets" size="34531" subdir="help" unzip="1" unzipped_size="79723" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/help/tagsets.zip" /> </packages> <collections> <collection id="all-nltk" name="All packages available on nltk_data gh-pages branch"> <item ref="abc" /> <item ref="alpino" /> <item ref="biocreative_ppi" /> <item ref="brown" /> <item ref="brown_tei" /> <item ref="cess_cat" /> <item ref="cess_esp" /> <item ref="chat80" /> <item ref="city_database" /> <item ref="cmudict" /> <item ref="comparative_sentences" /> <item ref="comtrans" /> <item ref="conll2000" /> <item ref="conll2002" /> <item ref="conll2007" /> <item ref="crubadan" /> <item ref="dependency_treebank" /> <item ref="europarl_raw" /> <item ref="floresta" /> <item ref="framenet_v15" /> <item ref="framenet_v17" /> <item ref="gazetteers" /> <item ref="genesis" /> <item ref="gutenberg" /> <item ref="ieer" /> <item ref="inaugural" /> <item ref="indian" /> <item ref="jeita" /> <item ref="kimmo" /> <item ref="knbc" /> <item ref="lin_thesaurus" /> <item ref="mac_morpho" /> <item ref="machado" /> <item ref="masc_tagged" /> <item ref="moses_sample" /> <item ref="movie_reviews" /> <item ref="names" /> <item ref="nombank.1.0" /> <item ref="nps_chat" /> <item ref="omw" /> <item ref="opinion_lexicon" /> <item ref="paradigms" /> <item ref="pil" /> <item ref="pl196x" /> <item ref="ppattach" /> <item ref="problem_reports" /> <item ref="propbank" /> <item ref="ptb" /> <item ref="product_reviews_1" /> <item ref="product_reviews_2" /> <item ref="pros_cons" /> <item ref="qc" /> <item ref="reuters" /> <item ref="rte" /> <item ref="semcor" /> <item ref="senseval" /> <item ref="sentiwordnet" /> <item ref="sentence_polarity" /> <item ref="shakespeare" /> <item ref="sinica_treebank" /> <item ref="smultron" /> <item ref="state_union" /> <item ref="stopwords" /> <item ref="subjectivity" /> <item ref="swadesh" /> <item ref="switchboard" /> <item ref="timit" /> <item ref="toolbox" /> <item ref="treebank" /> <item ref="twitter_samples" /> <item ref="udhr" /> <item ref="udhr2" /> <item ref="unicode_samples" /> <item ref="universal_treebanks_v20" /> <item ref="verbnet" /> <item ref="verbnet3" /> <item ref="webtext" /> <item ref="wordnet" /> <item ref="wordnet_ic" /> <item ref="words" /> <item ref="ycoe" /> <item ref="rslp" /> <item ref="maxent_treebank_pos_tagger" /> <item ref="universal_tagset" /> <item ref="maxent_ne_chunker" /> <item ref="punkt" /> <item ref="book_grammars" /> <item ref="sample_grammars" /> <item ref="spanish_grammars" /> <item ref="basque_grammars" /> <item ref="large_grammars" /> <item ref="tagsets" /> <item ref="snowball_data" /> <item ref="bllip_wsj_no_aux" /> <item ref="word2vec_sample" /> <item ref="panlex_swadesh" /> <item ref="mte_teip5" /> <item ref="averaged_perceptron_tagger" /> <item ref="averaged_perceptron_tagger_ru" /> <item ref="perluniprops" /> <item ref="nonbreaking_prefixes" /> <item ref="vader_lexicon" /> <item ref="porter_test" /> <item ref="wmt15_eval" /> <item ref="mwa_ppdb" /> </collection> <collection id="book" name="Everything used in the NLTK Book"> <item ref="abc" /> <item ref="brown" /> <item ref="chat80" /> <item ref="cmudict" /> <item ref="conll2000" /> <item ref="conll2002" /> <item ref="dependency_treebank" /> <item ref="genesis" /> <item ref="gutenberg" /> <item ref="ieer" /> <item ref="inaugural" /> <item ref="movie_reviews" /> <item ref="nps_chat" /> <item ref="names" /> <item ref="ppattach" /> <item ref="reuters" /> <item ref="senseval" /> <item ref="state_union" /> <item ref="stopwords" /> <item ref="swadesh" /> <item ref="timit" /> <item ref="treebank" /> <item ref="toolbox" /> <item ref="udhr" /> <item ref="udhr2" /> <item ref="unicode_samples" /> <item ref="webtext" /> <item ref="wordnet" /> <item ref="wordnet_ic" /> <item ref="words" /> <item ref="maxent_treebank_pos_tagger" /> <item ref="maxent_ne_chunker" /> <item ref="universal_tagset" /> <item ref="punkt" /> <item ref="book_grammars" /> <item ref="city_database" /> <item ref="tagsets" /> <item ref="panlex_swadesh" /> <item ref="averaged_perceptron_tagger" /> </collection> <collection id="third-party" name="Third-party data packages"> <item ref="dolch" /> </collection> <collection id="all" name="All packages"> <item ref="abc" /> <item ref="alpino" /> <item ref="biocreative_ppi" /> <item ref="brown" /> <item ref="brown_tei" /> <item ref="cess_cat" /> <item ref="cess_esp" /> <item ref="chat80" /> <item ref="city_database" /> <item ref="cmudict" /> <item ref="comparative_sentences" /> <item ref="comtrans" /> <item ref="conll2000" /> <item ref="conll2002" /> <item ref="conll2007" /> <item ref="crubadan" /> <item ref="dependency_treebank" /> <item ref="dolch" /> <item ref="europarl_raw" /> <item ref="floresta" /> <item ref="framenet_v15" /> <item ref="framenet_v17" /> <item ref="gazetteers" /> <item ref="genesis" /> <item ref="gutenberg" /> <item ref="ieer" /> <item ref="inaugural" /> <item ref="indian" /> <item ref="jeita" /> <item ref="kimmo" /> <item ref="knbc" /> <item ref="lin_thesaurus" /> <item ref="mac_morpho" /> <item ref="machado" /> <item ref="masc_tagged" /> <item ref="moses_sample" /> <item ref="movie_reviews" /> <item ref="names" /> <item ref="nombank.1.0" /> <item ref="nps_chat" /> <item ref="omw" /> <item ref="opinion_lexicon" /> <item ref="paradigms" /> <item ref="pil" /> <item ref="pl196x" /> <item ref="ppattach" /> <item ref="problem_reports" /> <item ref="propbank" /> <item ref="ptb" /> <item ref="product_reviews_1" /> <item ref="product_reviews_2" /> <item ref="pros_cons" /> <item ref="qc" /> <item ref="reuters" /> <item ref="rte" /> <item ref="semcor" /> <item ref="senseval" /> <item ref="sentiwordnet" /> <item ref="sentence_polarity" /> <item ref="shakespeare" /> <item ref="sinica_treebank" /> <item ref="smultron" /> <item ref="state_union" /> <item ref="stopwords" /> <item ref="subjectivity" /> <item ref="swadesh" /> <item ref="switchboard" /> <item ref="timit" /> <item ref="toolbox" /> <item ref="treebank" /> <item ref="twitter_samples" /> <item ref="udhr" /> <item ref="udhr2" /> <item ref="unicode_samples" /> <item ref="universal_treebanks_v20" /> <item ref="verbnet" /> <item ref="verbnet3" /> <item ref="webtext" /> <item ref="wordnet" /> <item ref="wordnet_ic" /> <item ref="words" /> <item ref="ycoe" /> <item ref="rslp" /> <item ref="maxent_treebank_pos_tagger" /> <item ref="universal_tagset" /> <item ref="maxent_ne_chunker" /> <item ref="punkt" /> <item ref="book_grammars" /> <item ref="sample_grammars" /> <item ref="spanish_grammars" /> <item ref="basque_grammars" /> <item ref="large_grammars" /> <item ref="tagsets" /> <item ref="snowball_data" /> <item ref="bllip_wsj_no_aux" /> <item ref="word2vec_sample" /> <item ref="panlex_swadesh" /> <item ref="mte_teip5" /> <item ref="averaged_perceptron_tagger" /> <item ref="averaged_perceptron_tagger_ru" /> <item ref="perluniprops" /> <item ref="nonbreaking_prefixes" /> <item ref="vader_lexicon" /> <item ref="porter_test" /> <item ref="wmt15_eval" /> <item ref="mwa_ppdb" /> </collection> <collection id="tests" name="Packages for running tests"> <item ref="averaged_perceptron_tagger" /> <item ref="porter_test" /> <item ref="twitter_samples" /> <item ref="wmt15_eval" /> <item ref="subjectivity" /> <item ref="framenet_v17" /> <item ref="product_reviews_1" /> <item ref="product_reviews_2" /> <item ref="vader_lexicon" /> <item ref="crubadan" /> <item ref="mte_teip5" /> <item ref="sentence_polarity" /> <item ref="universal_treebanks_v20" /> <item ref="panlex_swadesh" /> <item ref="nonbreaking_prefixes" /> <item ref="perluniprops" /> <item ref="pros_cons" /> <item ref="opinion_lexicon" /> <item ref="comparative_sentences" /> </collection> <collection id="all-corpora" name="All the corpora"> <item ref="abc" /> <item ref="alpino" /> <item ref="biocreative_ppi" /> <item ref="brown" /> <item ref="brown_tei" /> <item ref="cess_cat" /> <item ref="cess_esp" /> <item ref="chat80" /> <item ref="city_database" /> <item ref="cmudict" /> <item ref="comtrans" /> <item ref="conll2000" /> <item ref="conll2002" /> <item ref="conll2007" /> <item ref="crubadan" /> <item ref="dependency_treebank" /> <item ref="dolch" /> <item ref="floresta" /> <item ref="framenet_v15" /> <item ref="framenet_v17" /> <item ref="gazetteers" /> <item ref="genesis" /> <item ref="gutenberg" /> <item ref="ieer" /> <item ref="inaugural" /> <item ref="indian" /> <item ref="jeita" /> <item ref="kimmo" /> <item ref="knbc" /> <item ref="lin_thesaurus" /> <item ref="mac_morpho" /> <item ref="machado" /> <item ref="masc_tagged" /> <item ref="movie_reviews" /> <item ref="names" /> <item ref="nombank.1.0" /> <item ref="nps_chat" /> <item ref="omw" /> <item ref="paradigms" /> <item ref="pil" /> <item ref="pl196x" /> <item ref="ppattach" /> <item ref="problem_reports" /> <item ref="propbank" /> <item ref="ptb" /> <item ref="qc" /> <item ref="reuters" /> <item ref="rte" /> <item ref="semcor" /> <item ref="senseval" /> <item ref="sentiwordnet" /> <item ref="shakespeare" /> <item ref="sinica_treebank" /> <item ref="state_union" /> <item ref="stopwords" /> <item ref="swadesh" /> <item ref="switchboard" /> <item ref="timit" /> <item ref="toolbox" /> <item ref="treebank" /> <item ref="udhr" /> <item ref="udhr2" /> <item ref="unicode_samples" /> <item ref="universal_treebanks_v20" /> <item ref="verbnet" /> <item ref="verbnet3" /> <item ref="webtext" /> <item ref="wordnet" /> <item ref="wordnet_ic" /> <item ref="words" /> <item ref="ycoe" /> <item ref="panlex_swadesh" /> <item ref="mte_teip5" /> <item ref="nonbreaking_prefixes" /> </collection> <collection id="popular" name="Popular packages"> <item ref="cmudict" /> <item ref="gazetteers" /> <item ref="genesis" /> <item ref="gutenberg" /> <item ref="inaugural" /> <item ref="movie_reviews" /> <item ref="names" /> <item ref="shakespeare" /> <item ref="stopwords" /> <item ref="treebank" /> <item ref="twitter_samples" /> <item ref="omw" /> <item ref="wordnet" /> <item ref="wordnet_ic" /> <item ref="words" /> <item ref="maxent_ne_chunker" /> <item ref="punkt" /> <item ref="snowball_data" /> <item ref="averaged_perceptron_tagger" /> </collection> </collections> </nltk_data>"""
导入解析库beautifuldoup，依次提取DOM中的某个标签–>属性
【code - 2】：`
from bs4 import BeautifulSoup soup = BeautifulSoup(xml) dom = soup.find_all('package',{"url":True}) for i in dom: print(i['url'])
输出结果:
https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/misc/perluniprops.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/misc/mwa_ppdb.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/tokenizers/punkt.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/stemmers/rslp.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/stemmers/porter_test.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/stemmers/snowball_data.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/chunkers/maxent_ne_chunker.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/moses_sample.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/bllip_wsj_no_aux.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/word2vec_sample.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/wmt15_eval.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/spanish_grammars.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/sample_grammars.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/large_grammars.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/book_grammars.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/grammars/basque_grammars.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/maxent_treebank_pos_tagger.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/averaged_perceptron_tagger.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/averaged_perceptron_tagger_ru.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/taggers/universal_tagset.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/sentiment/vader_lexicon.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/lin_thesaurus.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/movie_reviews.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/problem_reports.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pros_cons.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/masc_tagged.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/sentence_polarity.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/webtext.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/nps_chat.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/city_database.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/europarl_raw.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/biocreative_ppi.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/verbnet3.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pe08.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pil.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/crubadan.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/gutenberg.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/propbank.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/machado.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/state_union.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/twitter_samples.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/semcor.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/names.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ptb.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/nombank.1.0.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/floresta.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/comtrans.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/knbc.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/mac_morpho.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/swadesh.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/rte.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/toolbox.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/jeita.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/product_reviews_1.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/omw.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/sentiwordnet.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/product_reviews_2.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/abc.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/udhr2.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/senseval.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/words.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/framenet_v15.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/unicode_samples.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/kimmo.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/framenet_v17.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/chat80.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/qc.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/inaugural.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/wordnet.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/stopwords.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/verbnet.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/shakespeare.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ycoe.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ieer.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/cess_cat.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/switchboard.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/comparative_sentences.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/subjectivity.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/udhr.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/pl196x.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/paradigms.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/gazetteers.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/timit.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/treebank.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/sinica_treebank.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/opinion_lexicon.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/ppattach.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/dependency_treebank.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/reuters.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/genesis.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/cess_esp.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/conll2007.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/nonbreaking_prefixes.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/dolch.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/smultron.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/alpino.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/wordnet_ic.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/brown.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/panlex_swadesh.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/conll2000.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/universal_treebanks_v20.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/brown_tei.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/cmudict.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/mte_teip5.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/indian.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/conll2002.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/help/tagsets.zip
记得点赞并关注噢！
