Revisions to Zim parsing, netflix parsing, and updates to html scraping to include synopsis

This commit is contained in:
prabhaavp
2026-03-19 01:56:14 -04:00
parent 0a70920ba9
commit 492160c3a3
13 changed files with 252 additions and 63 deletions

8
.idea/.gitignore generated vendored Normal file
View File

@@ -0,0 +1,8 @@
# Default ignored files
/shelf/
/workspace.xml
# Editor-based HTTP Client requests
/httpRequests/
# Datasource local storage ignored files
/dataSources/
/dataSources.local.xml

11
.idea/datamining_881_new.iml generated Normal file
View File

@@ -0,0 +1,11 @@
<?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" />
<excludeFolder url="file://$MODULE_DIR$/data/processed/wikipedia_html" />
</content>
<orderEntry type="jdk" jdkName="Python 3.13 (datamining_881_new)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

View File

@@ -0,0 +1,13 @@
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
<inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredIdentifiers">
<list>
<option value="dict.*" />
</list>
</option>
</inspection_tool>
</profile>
</component>

View File

@@ -0,0 +1,6 @@
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>

7
.idea/misc.xml generated Normal file
View File

@@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="Black">
<option name="sdkName" value="Python 3.13 (datamining_881_new)" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.13 (datamining_881_new)" project-jdk-type="Python SDK" />
</project>

8
.idea/modules.xml generated Normal file
View File

@@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/datamining_881_new.iml" filepath="$PROJECT_DIR$/.idea/datamining_881_new.iml" />
</modules>
</component>
</project>

7
.idea/vcs.xml generated Normal file
View File

@@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="" vcs="Git" />
<mapping directory="$PROJECT_DIR$" vcs="Git" />
</component>
</project>