Actor and Movie Scraper methods complete

.idea/WikiScraper.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="JavaScriptSettings">
+    <option name="languageLevel" value="ES6" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7 (WikiScraper)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/WikiScraper.iml" filepath="$PROJECT_DIR$/.idea/WikiScraper.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/workspace.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="dfe2fe6a-3b29-4f33-b3fd-eafecb9dc6a7" name="Default Changelist" comment="" />
+    <option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="ProjectId" id="1Rwnrzhl8nBDhVHFvVOBCr8JfkC" />
+  <component name="PropertiesComponent">
+    <property name="WebServerToolWindowFactoryState" value="false" />
+    <property name="settings.editor.selected.configurable" value="com.jetbrains.python.configuration.PyActiveSdkModuleConfigurable" />
+  </component>
+  <component name="RunDashboard">
+    <option name="ruleStates">
+      <list>
+        <RuleState>
+          <option name="name" value="ConfigurationTypeDashboardGroupingRule" />
+        </RuleState>
+        <RuleState>
+          <option name="name" value="StatusDashboardGroupingRule" />
+        </RuleState>
+      </list>
+    </option>
+  </component>
+  <component name="RunManager" selected="Python.Main">
+    <configuration name="ActorScraper" type="PythonConfigurationType" factoryName="Python" temporary="true">
+      <module name="WikiScraper" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="true" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/ActorScraper.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+    <configuration name="Main" type="PythonConfigurationType" factoryName="Python" temporary="true">
+      <module name="WikiScraper" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="true" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/Main.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+    <configuration name="MovieScraper" type="PythonConfigurationType" factoryName="Python" temporary="true">
+      <module name="WikiScraper" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="true" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/MovieScraper.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+    <recent_temporary>
+      <list>
+        <item itemvalue="Python.Main" />
+        <item itemvalue="Python.ActorScraper" />
+        <item itemvalue="Python.MovieScraper" />
+      </list>
+    </recent_temporary>
+  </component>
+  <component name="SvnConfiguration">
+    <configuration />
+  </component>
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="dfe2fe6a-3b29-4f33-b3fd-eafecb9dc6a7" name="Default Changelist" comment="" />
+      <created>1570587229309</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1570587229309</updated>
+      <workItem from="1570587232486" duration="20750000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="1" />
+  </component>
+  <component name="com.intellij.coverage.CoverageDataManagerImpl">
+    <SUITE FILE_PATH="coverage/WikiScraper$Main.coverage" NAME="Main Coverage Results" MODIFIED="1570616606717" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+    <SUITE FILE_PATH="coverage/WikiScraper$ActorScraper.coverage" NAME="ActorScraper Coverage Results" MODIFIED="1570615541260" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+    <SUITE FILE_PATH="coverage/WikiScraper$MovieScraper.coverage" NAME="MovieScraper Coverage Results" MODIFIED="1570613310487" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+  </component>
+</project>
\ No newline at end of file

ActorScraper.py

+import urllib.request as request
+from bs4 import BeautifulSoup
+import re
+import logging
+
+
+def scrape_actor(url):
+    logging.basicConfig(filename="./logs/ActorScraper_logs.log")
+
+    page = request.urlopen(url).read()
+    page = BeautifulSoup(page, "html.parser")
+    page.prettify()
+
+    vcard = page.find("table", {"class": "infobox biography vcard"})
+    if vcard is None:
+        logging.error("Actor vcard not found. Stopping search")
+        return
+
+    actor_name = ""
+    found_name = vcard.find("div", {"class": "fn"})
+    if found_name is None:
+        logging.warning("The actor's name could not be found")
+    else:
+        logging.info("The actor's name was found")
+        actor_name = found_name.get_text()
+
+    actor_age = -1
+    found_age = vcard.find("span", {"class": "noprint ForceAgeToShow"})
+    if found_age is None:
+        logging.warning("The actor's age could not be found")
+    else:
+        logging.info("The actor's age was found")
+        actor_age = re.sub("[^0-9]", "", found_age.contents[0])
+
+    actor_movies = []
+    filmography = page.find("span", {"id": "Filmography"})
+    if filmography is None:
+        logging.warning("The actor's films could not be found")
+    else:
+        logging.info("The actor's films were found")
+        film_list = filmography.find_next("ul")
+        film_table = filmography.find_next("tbody")
+
+        for film in film_list.findAll("i"):
+            movie_item = film.find("a")
+            if movie_item is None:
+                continue
+            movie_name = movie_item.get_text()
+            movie_link = "https://en.wikipedia.org" + movie_item.get("href")
+            actor_movies.append([movie_name, movie_link])
+
+        if len(film_list) == 0:
+            for film in film_table.findAll("td"):
+                movie_item = film.find("a")
+                if movie_item is None:
+                    continue
+                movie_name = movie_item.get_text()
+                movie_link = "https://en.wikipedia.org" + movie_item.get("href")
+                actor_movies.append([movie_name, movie_link])
+
+    actor_json = {
+        "url": url,
+        "name": actor_name,
+        "age": actor_age,
+        "movies": actor_movies
+    }
+
+    return actor_json
+
+
+#print(scrape_actor("https://en.wikipedia.org/wiki/Piper_Perabo"))

Main.py

+import ActorScraper
+import MovieScraper
+
+movie_list = []
+actor_list = []
+
+catalyst_movie_url = "https://en.wikipedia.org/wiki/Ted_2"
+catalyst_json = MovieScraper.scrape_movie(catalyst_movie_url)
+movie_list.append(catalyst_json)
+
+while len(movie_list) < 125 or len(actor_list) < 250:
+    if len(actor_list) < 125:
+        for movie in movie_list:
+            if "cast" in movie:
+                actors = movie["cast"]
+            else:
+                continue
+            for actor in actors:
+                if not any(actor[0] == i["name"] for i in actor_list):
+                    print(actor)
+                    actor_details = ActorScraper.scrape_actor(actor[1])
+                    actor_list.append(actor_details)
+
+    if len(movie_list) < 125:
+        for actor in actor_list:
+            movies = actor["movies"]
+            for movie in movies:
+                if not any(movie[0] == i["name"] for i in movie_list):
+                    print(movie)
+                    movie_details = MovieScraper.scrape_movie(movie[1])
+                    movie_list.append(actor_details)
+
+print(len(actor_list))
+print(len(movie_list))
\ No newline at end of file

MovieScraper.py

+from bs4 import BeautifulSoup
+import urllib.request as request
+import logging
+
+
+def scrape_movie(url):
+    logging.basicConfig(filename="./logs/MovieScraper_logs.log")
+
+    page = request.urlopen(url).read()
+    page = BeautifulSoup(page, "html.parser")
+    page.prettify()
+
+    infobox = page.find("table", {"class": "infobox vevent"})
+    if infobox is None:
+        logging.error("Movie info box not found. Stopping search.")
+        return
+
+    movie_name = ""
+    found_name = infobox.find("th", {"class": "summary"})
+    if found_name is None:
+        logging.warning("Movie name could not be found")
+    else:
+        logging.info("Movie name was found")
+        movie_name = found_name.text
+
+    movie_gross = -1
+    found_gross = infobox.find(text="Box office")
+    if found_gross is None:
+        logging.warning("Movie gross could not be found")
+    else:
+        logging.info("Movie gross was found")
+        movie_gross = found_gross.find_next("td").contents[0]
+
+    movie_cast = []
+    found_cast = infobox.find(text="Starring")
+    if found_cast is None:
+        logging.warning("Movie cast could not be found")
+    else:
+        logging.info("Movie cast was found")
+        found_cast = found_cast.find_next("ul")
+        cast_a_list = found_cast.findAll("a")
+
+        for cast_member in cast_a_list:
+            cast_member_name = cast_member.get_text()
+            cast_member_link = "https://en.wikipedia.org" + cast_member.get("href")
+            movie_cast.append([cast_member_name, cast_member_link])
+
+    movies_json = {
+        "url": url,
+        "name": movie_name,
+        "gross": movie_gross,
+        "cast": movie_cast
+    }
+
+    return movies_json
+
+
+#print(scrape_movie("https://en.wikipedia.org/wiki/The_Dark_Knight_(film)"))

venv/Lib/site-packages/beautifulsoup4-4.8.1.dist-info/DESCRIPTION.rst

+Beautiful Soup is a library that makes it easy to scrape information
+from web pages. It sits atop an HTML or XML parser, providing Pythonic
+idioms for iterating, searching, and modifying the parse tree.
+
+# Quick start
+
+```
+>>> from bs4 import BeautifulSoup
+>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
+>>> print soup.prettify()
+<html>
+<body>
+<p>
+Some
+<b>
+bad
+<i>
+HTML
+</i>
+</b>
+</p>
+</body>
+</html>
+>>> soup.find(text="bad")
+u'bad'
+>>> soup.i
+<i>HTML</i>
+#
+>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
+#
+>>> print soup.prettify()
+<?xml version="1.0" encoding="utf-8">
+<tag1>
+Some
+<tag2 />
+bad
+<tag3>
+XML
+</tag3>
+</tag1>
+```
+
+To go beyond the basics, [comprehensive documentation is available](http://www.crummy.com/software/BeautifulSoup/bs4/doc/).
+
+# Links
+
+* [Homepage](http://www.crummy.com/software/BeautifulSoup/bs4/)
+* [Documentation](http://www.crummy.com/software/BeautifulSoup/bs4/doc/)
+* [Discussion group](http://groups.google.com/group/beautifulsoup/)
+* [Development](https://code.launchpad.net/beautifulsoup/)
+* [Bug tracker](https://bugs.launchpad.net/beautifulsoup/)
+* [Complete changelog](https://bazaar.launchpad.net/~leonardr/beautifulsoup/bs4/view/head:/CHANGELOG)
+
+# Note on Python 2 sunsetting
+
+Since 2012, Beautiful Soup has been developed as a Python 2 library
+which is automatically converted to Python 3 code as necessary. This
+makes it impossible to take advantages of some features of Python
+3.
+
+For this reason, I plan to discontinue Beautiful Soup's Python 2
+support at some point after January 1, 2021: one year after the sunset
+date for Python 2 itself. Beyond that point, new Beautiful Soup
+development will exclusively target Python 3. Of course, older
+releases of Beautiful Soup, which support both versions, will continue
+to be available.
+
+# Supporting the project
+
+If you use Beautiful Soup as part of your professional work, please consider a
+[Tidelift subscription](https://tidelift.com/subscription/pkg/pypi-beautifulsoup4?utm_source=pypi-beautifulsoup4&utm_medium=referral&utm_campaign=readme).
+This will support many of the free software projects your organization
+depends on, not just Beautiful Soup.
+
+If you use Beautiful Soup for personal projects, the best way to say
+thank you is to read
+[Tool Safety](https://www.crummy.com/software/BeautifulSoup/zine/), a zine I
+wrote about what Beautiful Soup has taught me about software
+development.
+
+# Building the documentation
+
+The bs4/doc/ directory contains full documentation in Sphinx
+format. Run `make html` in that directory to create HTML
+documentation.
+
+# Running the unit tests
+
+Beautiful Soup supports unit test discovery from the project root directory:
+
+```
+$ nosetests
+```
+
+```
+$ python -m unittest discover -s bs4
+```
+
+If you checked out the source tree, you should see a script in the
+home directory called test-all-versions. This script will run the unit
+tests under Python 2, then create a temporary Python 3 conversion of
+the source and run the unit tests again under Python 3.
+
+

venv/Lib/site-packages/beautifulsoup4-4.8.1.dist-info/INSTALLER

+pip

venv/Lib/site-packages/beautifulsoup4-4.8.1.dist-info/METADATA

+Metadata-Version: 2.0
+Name: beautifulsoup4
+Version: 4.8.1
+Summary: Screen-scraping library
+Home-page: http://www.crummy.com/software/BeautifulSoup/bs4/
+Author: Leonard Richardson
+Author-email: leonardr@segfault.org
+License: MIT
+Download-URL: http://www.crummy.com/software/BeautifulSoup/bs4/download/
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 2.7
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: XML
+Classifier: Topic :: Text Processing :: Markup :: SGML
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: soupsieve (>=1.2)
+Provides-Extra: html5lib
+Requires-Dist: html5lib; extra == 'html5lib'
+Provides-Extra: lxml
+Requires-Dist: lxml; extra == 'lxml'
+
+Beautiful Soup is a library that makes it easy to scrape information
+from web pages. It sits atop an HTML or XML parser, providing Pythonic
+idioms for iterating, searching, and modifying the parse tree.
+
+# Quick start
+
+```
+>>> from bs4 import BeautifulSoup
+>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
+>>> print soup.prettify()
+<html>
+<body>
+<p>
+Some
+<b>
+bad
+<i>
+HTML
+</i>
+</b>
+</p>
+</body>
+</html>
+>>> soup.find(text="bad")
+u'bad'
+>>> soup.i
+<i>HTML</i>
+#
+>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
+#
+>>> print soup.prettify()
+<?xml version="1.0" encoding="utf-8">
+<tag1>
+Some
+<tag2 />
+bad
+<tag3>
+XML
+</tag3>
+</tag1>
+```
+
+To go beyond the basics, [comprehensive documentation is available](http://www.crummy.com/software/BeautifulSoup/bs4/doc/).
+
+# Links
+
+* [Homepage](http://www.crummy.com/software/BeautifulSoup/bs4/)
+* [Documentation](http://www.crummy.com/software/BeautifulSoup/bs4/doc/)
+* [Discussion group](http://groups.google.com/group/beautifulsoup/)
+* [Development](https://code.launchpad.net/beautifulsoup/)
+* [Bug tracker](https://bugs.launchpad.net/beautifulsoup/)
+* [Complete changelog](https://bazaar.launchpad.net/~leonardr/beautifulsoup/bs4/view/head:/CHANGELOG)
+
+# Note on Python 2 sunsetting
+
+Since 2012, Beautiful Soup has been developed as a Python 2 library
+which is automatically converted to Python 3 code as necessary. This
+makes it impossible to take advantages of some features of Python
+3.
+
+For this reason, I plan to discontinue Beautiful Soup's Python 2
+support at some point after January 1, 2021: one year after the sunset
+date for Python 2 itself. Beyond that point, new Beautiful Soup
+development will exclusively target Python 3. Of course, older
+releases of Beautiful Soup, which support both versions, will continue
+to be available.
+
+# Supporting the project
+
+If you use Beautiful Soup as part of your professional work, please consider a
+[Tidelift subscription](https://tidelift.com/subscription/pkg/pypi-beautifulsoup4?utm_source=pypi-beautifulsoup4&utm_medium=referral&utm_campaign=readme).
+This will support many of the free software projects your organization
+depends on, not just Beautiful Soup.
+
+If you use Beautiful Soup for personal projects, the best way to say
+thank you is to read
+[Tool Safety](https://www.crummy.com/software/BeautifulSoup/zine/), a zine I
+wrote about what Beautiful Soup has taught me about software
+development.
+
+# Building the documentation
+
+The bs4/doc/ directory contains full documentation in Sphinx
+format. Run `make html` in that directory to create HTML
+documentation.
+
+# Running the unit tests
+
+Beautiful Soup supports unit test discovery from the project root directory:
+
+```
+$ nosetests
+```
+
+```
+$ python -m unittest discover -s bs4
+```
+
+If you checked out the source tree, you should see a script in the
+home directory called test-all-versions. This script will run the unit
+tests under Python 2, then create a temporary Python 3 conversion of
+the source and run the unit tests again under Python 3.
+
+

venv/Lib/site-packages/beautifulsoup4-4.8.1.dist-info/RECORD

+beautifulsoup4-4.8.1.dist-info/DESCRIPTION.rst,sha256=TUEndO1FnBoCMGIeuX9tkAhKSylXB1t_NUSYxDo6ce4,3010
+beautifulsoup4-4.8.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+beautifulsoup4-4.8.1.dist-info/METADATA,sha256=ZQSTtI3Y6TP3LVrckhEel5QhfhqT8pwwvBuronGBz34,4020
+beautifulsoup4-4.8.1.dist-info/RECORD,,
+beautifulsoup4-4.8.1.dist-info/WHEEL,sha256=rNo05PbNqwnXiIHFsYm0m22u4Zm6YJtugFG2THx4w3g,92
+beautifulsoup4-4.8.1.dist-info/metadata.json,sha256=RNf83TEq3M65TUoCk_oElvbCdiLyo_AQuj0f7SNVEGc,1144
+beautifulsoup4-4.8.1.dist-info/top_level.txt,sha256=H8VT-IuPWLzQqwG9_eChjXDJ1z0H9RRebdSR90Bjnkw,4
+bs4/__init__.py,sha256=VF0X3wc9hsmeJiMt630mwChrwIc58DYt4c9vP2ky-w4,25903
+bs4/__pycache__/__init__.cpython-37.pyc,,
+bs4/__pycache__/check_block.cpython-37.pyc,,
+bs4/__pycache__/dammit.cpython-37.pyc,,
+bs4/__pycache__/diagnose.cpython-37.pyc,,
+bs4/__pycache__/element.cpython-37.pyc,,
+bs4/__pycache__/formatter.cpython-37.pyc,,
+bs4/__pycache__/testing.cpython-37.pyc,,
+bs4/builder/__init__.py,sha256=e_vTLD3AkgUTjUXkc04b0FZHJBRaVM8SDxvVNMnLXtE,14749
+bs4/builder/__pycache__/__init__.cpython-37.pyc,,
+bs4/builder/__pycache__/_html5lib.cpython-37.pyc,,
+bs4/builder/__pycache__/_htmlparser.cpython-37.pyc,,
+bs4/builder/__pycache__/_lxml.cpython-37.pyc,,
+bs4/builder/_html5lib.py,sha256=105ocel2oFeApKaPem5XtjL67kO5rKJxM5_6B2gxBw0,18088
+bs4/builder/_htmlparser.py,sha256=AKpOnUAoPBYi7x0Y1fTb1Uxrxb2EFroWIdCWgwShcF4,13653
+bs4/builder/_lxml.py,sha256=BsJBgIoyIZYY001TSHLtEsJtYD5hCXhldwpUEaYaJkg,11114
+bs4/check_block.py,sha256=ltAO73VRGrGcO0bVPMd0GdTlIg9eVTCGnnZiPbKzFI0,132
+bs4/dammit.py,sha256=VcHa3eSGP6bL3UuCrjMy_auYO7tTH42I-lhNDbrMsy8,31028
+bs4/diagnose.py,sha256=wvGDZf6VNj6rwDjU3xOsz90z2KZiBWgpu-GRqWfR6is,6966
+bs4/element.py,sha256=ebosrK3jVgnZ4Dr7kmrJdfRUu8JkENXKQHwNKPcA2QE,59447
+bs4/formatter.py,sha256=G2AYBRjeX404vLNwIPbjiG8KDjuoCqrgi9NHua6o34M,3199
+bs4/testing.py,sha256=MBsN77WRpB1Z78Y0pV7RlwbMWGfEU1iPySFKE-JJIgc,41306
+bs4/tests/__init__.py,sha256=bdUBDE750n7qNEfue7-3a1fBaUxJlvZMkvJvZa-lbYs,27
+bs4/tests/__pycache__/__init__.cpython-37.pyc,,
+bs4/tests/__pycache__/test_builder_registry.cpython-37.pyc,,
+bs4/tests/__pycache__/test_docs.cpython-37.pyc,,
+bs4/tests/__pycache__/test_html5lib.cpython-37.pyc,,
+bs4/tests/__pycache__/test_htmlparser.cpython-37.pyc,,
+bs4/tests/__pycache__/test_lxml.cpython-37.pyc,,
+bs4/tests/__pycache__/test_soup.cpython-37.pyc,,
+bs4/tests/__pycache__/test_tree.cpython-37.pyc,,
+bs4/tests/test_builder_registry.py,sha256=pllfRpArh9TYhjjRUiu1wITr9Ryyv4hiaAtRjij-k4E,5582
+bs4/tests/test_docs.py,sha256=FXfz2bGL4Xe0q6duwpmg9hmFiZuU4DVJPNZ0hTb6aH4,1067
+bs4/tests/test_html5lib.py,sha256=R2zNUUbUa3WnSqGGOiARKDWH1TLguogluqQDr10Gick,6493
+bs4/tests/test_htmlparser.py,sha256=N-wPX5jDOy7b8xUv9pHEIEfEFjOitLuD9V1blKcbscM,2354
+bs4/tests/test_lxml.py,sha256=xJr8eDrtHSb_vQw88lYEKyfdM1Hel4-dBaz14vQq78M,4105
+bs4/tests/test_soup.py,sha256=JbjlyIKCmUnVNfEHq3aPjyj-w7WZEgE9cAV-LOx6xwo,27613
+bs4/tests/test_tree.py,sha256=XBRpEOpAEvDhOeSSN857U5OcjdvfqmYT3bDNN8Qbabw,86259

venv/Lib/site-packages/beautifulsoup4-4.8.1.dist-info/WHEEL

+Wheel-Version: 1.0
+Generator: bdist_wheel (0.29.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

venv/Lib/site-packages/beautifulsoup4-4.8.1.dist-info/metadata.json

+{"classifiers": ["Development Status :: 5 - Production/Stable", "Intended Audience :: Developers", "License :: OSI Approved :: MIT License", "Programming Language :: Python", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3", "Topic :: Text Processing :: Markup :: HTML", "Topic :: Text Processing :: Markup :: XML", "Topic :: Text Processing :: Markup :: SGML", "Topic :: Software Development :: Libraries :: Python Modules"], "download_url": "http://www.crummy.com/software/BeautifulSoup/bs4/download/", "extensions": {"python.details": {"contacts": [{"email": "leonardr@segfault.org", "name": "Leonard Richardson", "role": "author"}], "document_names": {"description": "DESCRIPTION.rst"}, "project_urls": {"Home": "http://www.crummy.com/software/BeautifulSoup/bs4/"}}}, "extras": ["html5lib", "lxml"], "generator": "bdist_wheel (0.29.0)", "license": "MIT", "metadata_version": "2.0", "name": "beautifulsoup4", "run_requires": [{"extra": "html5lib", "requires": ["html5lib"]}, {"extra": "lxml", "requires": ["lxml"]}, {"requires": ["soupsieve (>=1.2)"]}], "summary": "Screen-scraping library", "version": "4.8.1"}
\ No newline at end of file

venv/Lib/site-packages/beautifulsoup4-4.8.1.dist-info/top_level.txt

+bs4