MANIFEST.in
setup.py
webcorpus/__init__.py
webcorpus/cli.py
webcorpus/sources.py
webcorpus/utils.py
webcorpus.egg-info/PKG-INFO
webcorpus.egg-info/SOURCES.txt
webcorpus.egg-info/dependency_links.txt
webcorpus.egg-info/entry_points.txt
webcorpus.egg-info/requires.txt
webcorpus.egg-info/top_level.txt
webcorpus/corpus/__init__.py
webcorpus/crawlers/__init__.py
webcorpus/crawlers/news.py
webcorpus/crawlers/settings.py
webcorpus/crawlers/w3newspaper.py
webcorpus/language/__init__.py
webcorpus/language/itrans_transliterator.py
webcorpus/language/langinfo.py
webcorpus/language/normalize.py
webcorpus/language/sentence_tokenize.py
webcorpus/language/sinhala_transliterator.py
webcorpus/language/tokenize.py
webcorpus/language/unicode_transliterate.py
webcorpus/processors/__init__.py
webcorpus/processors/agcsent.py
webcorpus/processors/annot_sent.py
webcorpus/processors/arts.py
webcorpus/processors/artsfile.py
webcorpus/processors/datedarts.py
webcorpus/processors/headline-pred.py
webcorpus/processors/sent.py
webcorpus/processors/tokenize.py
webcorpus/processors/topic.py