ArchiveTeam/Migrated_ArchiveTeam_Project_URL_Extractor
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated to include doi.org extraction

Browse Source
This commit is contained in:
datechnoman 2024-06-02 08:13:22 +00:00
parent 39afb55120
commit b4f357090f
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
archiveteam_project_url_extractor.py
View File

@ -77,7 +77,8 @@ url_patterns = {
r'(mediafire\.com|mfi\.re)\S+': 'filtered_mediafire_mfi.re.txt', r'(mediafire\.com|mfi\.re)\S+': 'filtered_mediafire_mfi.re.txt',
r'\S*imgur\S*': 'filtered_imgur.txt', r'\S*imgur\S*': 'filtered_imgur.txt',
r'http(s)?://(www\.)?pastebin.com': 'filtered_pastebin.txt', r'http(s)?://(www\.)?pastebin.com': 'filtered_pastebin.txt',
r'https?://\S+\.pdf\b': 'filtered_pdf_files.txt' r'https?://\S+\.pdf\b': 'filtered_pdf_files.txt',
r'https?://(www\.)?doi\.org\S*': 'filtered_doi_org.txt'
} }
# Ask the user for the number of concurrent instances # Ask the user for the number of concurrent instances