bellingcat/snscrape
1
0
Fork 0
mirror of https://github.com/bellingcat/snscrape.git synced 2026-06-11 20:08:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Force TwitterThreadScraper and TwitterListMembersScraper to fetch the old design

Browse Source
This commit is contained in:
JustAnotherArchivist
2020-03-04 00:40:23 +00:00
parent 613395d1c2
commit b6cc3180d9
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
snscrape/modules/twitter.py
View File

@@ -247,7 +247,7 @@ class TwitterThreadScraper(TwitterCommonScraper):
self._tweetID = tweetID
def get_items(self):
headers = {'User-Agent': f'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.{random.randint(1, 3500)}.{random.randint(1, 160)} Safari/537.36'}
headers = {'User-Agent': f'Opera/9.80 (Windows NT 6.1; WOW64) Presto/2.12.388 Version/12.18'}
# Fetch the page of the last tweet in the thread
r = self._get(f'https://twitter.com/user/status/{self._tweetID}', headers = headers)
@@ -325,7 +325,7 @@ class TwitterListMembersScraper(TwitterCommonScraper):
self._user, self._list = listName.split('/')
def get_items(self):
headers = {'User-Agent': f'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.{random.randint(1, 3500)}.{random.randint(1, 160)} Safari/537.36'}
headers = {'User-Agent': f'Opera/9.80 (Windows NT 6.1; WOW64) Presto/2.12.388 Version/12.18'}
baseUrl = f'https://twitter.com/{self._user}/lists/{self._list}/members'
r = self._get(baseUrl, headers = headers)