mathdatech/twoot
1
0
Fork 0
mirror of https://gitlab.com/jeancf/twoot.git synced 2025-05-08 12:33:56 +00:00
Code Issues 1 Packages Projects Releases Wiki Activity

Added code to remove trackers from fragments

Browse Source
This commit is contained in:
jeancf 2022-11-22 22:01:27 +01:00
parent 9b5a76db60
commit 0d1be42dcc
1 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
twoot.py
View File

@ -110,13 +110,18 @@ def _remove_trackers_query(query_str):
# tag by TikTok # tag by TikTok
# tags by Snapchat # tags by Snapchat
# tags by Facebook # tags by Facebook
params_to_remove = [ params_to_remove = {
"utm_source", "utm_medium", "utm_campaign", "utm_term", "utm_content", "gclid", "_ga", "gclsrc", "dclid",
"utm_source", "utm_medium", "utm_campaign", "utm_term", "utm_content", "utm_cid", "utm_reader", "utm_name", "utm_referrer", "utm_social", "utm_social-type",
"mkt_tok", "mkt_tok",
"campaign_name", "ad_set_name", "campaign_id", "ad_set_id", "campaign_name", "ad_set_name", "campaign_id", "ad_set_id",
"media", "interest_group_name", "fbclid", "campaign_name", "ad_set_name", "ad_set_id", "media", "interest_group_name", "ad_set_id"
"xtor" "igshid",
] "cvid", "oicd", "msclkid",
"soc_src", "soc_trk",
"_openstat", "yclid",
"xtor", "xtref", "adid",
}
query_to_clean = dict(parse_qsl(query_str, keep_blank_values=True)) query_to_clean = dict(parse_qsl(query_str, keep_blank_values=True))
query_cleaned = [(k, v) for k, v in query_to_clean.items() if not k in params_to_remove] query_cleaned = [(k, v) for k, v in query_to_clean.items() if not k in params_to_remove]
return urlencode(query_cleaned, doseq=True) return urlencode(query_cleaned, doseq=True)
@ -129,12 +134,15 @@ def _remove_trackers_fragment(fragment_str):
:param query_str: fragment to be cleaned :param query_str: fragment to be cleaned
:return: cleaned fragment :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/
params_to_remove = {
"Echobox",
}
if '=' in fragment_str:
fragment_str = fragment_str.split('&')
query_cleaned = [i for i in fragment_str if i.split('=')[0] not in params_to_remove]
fragment_str = '&'.join(query_cleaned)
return fragment_str return fragment_str