Handle simple obfuscations - HomeDepot.com style price obfuscation (#764)

This commit is contained in:
dgtlmoon
2022-07-20 13:42:09 +02:00
parent a95468be08
commit dd0eeca056
4 changed files with 59 additions and 4147 deletions

View File

@@ -150,7 +150,9 @@ class perform_site_check():
is_html = False
if is_html or is_source:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
html_content = fetcher.content
# If not JSON, and if it's not text/plain..