mathdatech/twoot
1
0
Fork 0
mirror of https://gitlab.com/jeancf/twoot.git synced 2024-11-27 14:01:13 +00:00
Code Issues 1 Packages Projects Releases Wiki Activity

Added option to scrape linked page if no pic is provided in tweet

Browse Source
This commit is contained in:
jeancf 2019-08-16 15:27:55 +02:00
parent 8059b062ac
commit 5b23c66b6b
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
twoot.py
View File

@ -213,6 +213,19 @@ def main(argv):
if len(videos) != 0:
tweet_text += '\n\n[Embedded video in original tweet]'
# If no media was specifically added in the tweet, try to get the first picture
# with "twitter:image" meta tag in first linked page in tweet text
if not photos:
m = re.search(r"http[^ \n\xa0]*", tweet_text)
if m is not None:
link_url = m.group(0)
r = requests.get(link_url)
if r.status_code == 200:
# Matches the first instance of either twitter:image or twitter:image:src meta tag
match = re.search(r'<meta name="twitter:image(?:|:src)" content="(.+?)".*?>', r.text)
if match is not None:
photos.append(match.group(1))
# Add dictionary with content of tweet to list
tweet = {
"author": author,