bellingcat/snscrape
1
0
Fork 0
mirror of https://github.com/bellingcat/snscrape.git synced 2026-06-12 12:28:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Handle tweets by temporarily blocked accounts (which show up in the search results but don't have a date or content)

Browse Source
This commit is contained in:
JustAnotherArchivist
2019-05-21 22:37:43 +00:00
parent e528ca3f26
commit 7989af27b5
1 changed files with 22 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
snscrape/modules/twitter.py
View File

@@ -48,18 +48,31 @@ class TwitterSearchScraper(snscrape.base.Scraper):
username = tweet.find('span', 'username').find('b').text username = tweet.find('span', 'username').find('b').text
tweetID = tweet['data-item-id'] tweetID = tweet['data-item-id']
url = f'https://twitter.com/{username}/status/{tweetID}' url = f'https://twitter.com/{username}/status/{tweetID}'
date = datetime.datetime.fromtimestamp(int(tweet.find('a', 'tweet-timestamp').find('span', '_timestamp')['data-time']), datetime.timezone.utc)
date = None
timestampA = tweet.find('a', 'tweet-timestamp')
if timestampA:
timestampSpan = timestampA.find('span', '_timestamp')
if timestampSpan and timestampSpan.has_attr('data-time'):
date = datetime.datetime.fromtimestamp(int(timestampSpan['data-time']), datetime.timezone.utc)
if not date:
logger.warning(f'Failed to extract date for {url}')
contentP = tweet.find('p', 'tweet-text') contentP = tweet.find('p', 'tweet-text')
content = contentP.text content = None
outlinks = [] outlinks = []
tcooutlinks = [] tcooutlinks = []
for a in contentP.find_all('a'): if contentP:
if a.has_attr('href') and not a['href'].startswith('/') and (not a.has_attr('class') or 'u-hidden' not in a['class']): content = contentP.text
if a.has_attr('data-expanded-url'): for a in contentP.find_all('a'):
outlinks.append(a['data-expanded-url']) if a.has_attr('href') and not a['href'].startswith('/') and (not a.has_attr('class') or 'u-hidden' not in a['class']):
else: if a.has_attr('data-expanded-url'):
logger.warning(f'Ignoring link without expanded URL on {url}: {a["href"]}') outlinks.append(a['data-expanded-url'])
tcooutlinks.append(a['href']) else:
logger.warning(f'Ignoring link without expanded URL on {url}: {a["href"]}')
tcooutlinks.append(a['href'])
else:
logger.warning(f'Failed to extract content for {url}')
card = tweet.find('div', 'card2') card = tweet.find('div', 'card2')
if card and 'has-autoplayable-media' not in card['class']: if card and 'has-autoplayable-media' not in card['class']:
for div in card.find_all('div'): for div in card.find_all('div'):