bellingcat/snscrape
1
0
Fork 0
mirror of https://github.com/bellingcat/snscrape.git synced 2026-06-13 04:48:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Use assignment expressions for cleaner code

Browse Source
This commit is contained in:
JustAnotherArchivist
2020-10-01 18:54:57 +00:00
parent 472cef2382
commit c72bf3174f
1 changed files with 3 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
snscrape/modules/telegram.py
View File

@@ -74,8 +74,7 @@ class TelegramChannelScraper(snscrape.base.Scraper):
yield post['data-post'].split('/')[0] yield post['data-post'].split('/')[0]
return return
date = datetime.datetime.strptime(post.find('div', class_ = 'tgme_widget_message_footer').find('a', class_ = 'tgme_widget_message_date').find('time', datetime = True)['datetime'].replace('-', '', 2).replace(':', ''), '%Y%m%dT%H%M%S%z') date = datetime.datetime.strptime(post.find('div', class_ = 'tgme_widget_message_footer').find('a', class_ = 'tgme_widget_message_date').find('time', datetime = True)['datetime'].replace('-', '', 2).replace(':', ''), '%Y%m%dT%H%M%S%z')
message = post.find('div', class_ = 'tgme_widget_message_text') if (message := post.find('div', class_ = 'tgme_widget_message_text')):
if message:
content = message.text content = message.text
outlinks = [] outlinks = []
for link in post.find_all('a'): for link in post.find_all('a'):
@@ -94,11 +93,9 @@ class TelegramChannelScraper(snscrape.base.Scraper):
outlinks = [] outlinks = []
outlinksss = '' outlinksss = ''
linkPreview = None linkPreview = None
linkPreviewA = post.find('a', class_ = 'tgme_widget_message_link_preview') if (linkPreviewA := post.find('a', class_ = 'tgme_widget_message_link_preview')):
if linkPreviewA:
image = None image = None
imageI = linkPreviewA.find('i', class_ = 'link_preview_image') if (imageI := linkPreviewA.find('i', class_ = 'link_preview_image')):
if imageI:
if imageI['style'].startswith("background-image:url('"): if imageI['style'].startswith("background-image:url('"):
image = imageI['style'][22 : imageI['style'].index("'", 22)] image = imageI['style'][22 : imageI['style'].index("'", 22)]
else: else: