mathdatech/twoot
1
0
Fork 0
mirror of https://gitlab.com/jeancf/twoot.git synced 2025-02-17 13:58:11 +00:00
Code Issues 1 Packages Projects Releases Wiki Activity

Added _remove_tracker_fragment()

Browse Source
This commit is contained in:
jeancf 2022-11-19 13:12:41 +01:00
parent 94294c6792
commit f88414bb35
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
twoot.py
View File

@ -67,7 +67,7 @@ USER_AGENTS = [
] ]
def _remove_tracker_params(query_str): def _remove_trackers_query(query_str):
""" """
private function private function
Given a query string from a URL, strip out the known trackers Given a query string from a URL, strip out the known trackers
@ -91,6 +91,22 @@ def _remove_tracker_params(query_str):
return urlencode(query_cleaned, doseq=True) return urlencode(query_cleaned, doseq=True)
def _remove_trackers_fragment(fragment_str):
"""
private function
Given a fragment string from a URL, strip out the known trackers
:param query_str: fragment to be cleaned
:return: cleaned fragment
"""
# Not implemented
# Unclear what, if anything, can be done
# Need better understanding of fragment-based tracking
# https://builtvisible.com/one-weird-trick-to-avoid-utm-parameters/
return fragment_str
def clean_url(dirty_url): def clean_url(dirty_url):
""" """
Given a URL, return it with the UTM parameters removed from query and fragment Given a URL, return it with the UTM parameters removed from query and fragment
@ -107,8 +123,8 @@ def clean_url(dirty_url):
url_parsed.netloc, url_parsed.netloc,
url_parsed.path, url_parsed.path,
url_parsed.params, url_parsed.params,
_remove_tracker_params(url_parsed.query), _remove_trackers_query(url_parsed.query),
_remove_tracker_params(url_parsed.fragment) _remove_trackers_fragment(url_parsed.fragment)
]) ])
if cleaned_url != dirty_url: if cleaned_url != dirty_url: