mathdatech/twoot
1
0
Fork 0
mirror of https://gitlab.com/jeancf/twoot.git synced 2025-01-18 23:37:05 +00:00
Code Issues 1 Packages Projects Releases Wiki Activity

Text and links are fixed

Browse Source
This commit is contained in:
jeancf 2020-02-14 16:37:54 +01:00
parent 9dbf40bb5d
commit 296d124c35
1 changed files with 18 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
twoot.py
View File

@ -66,11 +66,17 @@ def cleanup_tweet_text(tt_iter):
# If element is an external link # If element is an external link
elif tc == 'twitter_external_link': elif tc == 'twitter_external_link':
# Add a sometimes missing space before url # If element is a simple link
if not tweet_text.endswith(' ') and not tweet_text.endswith('\n'): if tag.has_attr('data-expanded-url'):
tweet_text += ' ' # Add a sometimes missing space before url
# Add full url if not tweet_text.endswith(' ') and not tweet_text.endswith('\n'):
tweet_text += tag['data-expanded-url'] tweet_text += ' '
# Add full url
tweet_text += tag['data-expanded-url']
# If element is a picture
elif tag.has_attr('data-url'):
# TODO handle photo
pass
# If element is hashflag (hashtag + icon), handle as simple hashtag # If element is hashflag (hashtag + icon), handle as simple hashtag
elif tag.name == 'span' and tag['class'][0] == 'twitter-hashflag-container': elif tag.name == 'span' and tag['class'][0] == 'twitter-hashflag-container':
@ -151,7 +157,7 @@ def main(argv):
# Verify that this is the no_js page that we expected # Verify that this is the no_js page that we expected
soup = BeautifulSoup(r1.text, 'html.parser') soup = BeautifulSoup(r1.text, 'html.parser')
assert (str(soup.form.p.string).find('JavaScript is disabled') != -1),\ assert 'JavaScript is disabled' in str(soup.form.p.string),\
'this is not the no_js page we expected. Quitting' 'this is not the no_js page we expected. Quitting'
# Submit POST form response with cookies # Submit POST form response with cookies
@ -175,13 +181,16 @@ def main(argv):
# Verify that we now have the correct twitter page # Verify that we now have the correct twitter page
soup = BeautifulSoup(response.text, 'html.parser') soup = BeautifulSoup(response.text, 'html.parser')
assert (str(soup.head.title.string).find(twit_account) != -1),\ assert twit_account.lower() in str(soup.head.title.string).lower(),\
'This is not the correct twitter page. Quitting' 'This is not the correct twitter page. Quitting'
# Extract twitter timeline # Extract twitter timeline
results = soup.find_all('table', class_='tweet') results = soup.find_all('table', class_='tweet')
for result in results: for result in results:
# Extract tweet id
tweet_id = str(result['href']).strip('?p=v')
# Isolate tweet header # Isolate tweet header
sih = result.find('tr', class_='tweet-header') sih = result.find('tr', class_='tweet-header')
@ -201,9 +210,6 @@ def main(argv):
# Isolate tweet text container # Isolate tweet text container
ttc = result.find('tr', class_='tweet-container') ttc = result.find('tr', class_='tweet-container')
# Extract tweet id
tweet_id = ttc.find('div', class_='tweet-text')['data-id']
# extract iterator over tweet text contents # extract iterator over tweet text contents
tt_iter = ttc.find('div', class_='dir-ltr').children tt_iter = ttc.find('div', class_='dir-ltr').children
@ -211,10 +217,10 @@ def main(argv):
# Check it the tweet is a retweet from somebody else # Check it the tweet is a retweet from somebody else
if author_account.lower() != twit_account.lower(): if author_account.lower() != twit_account.lower():
tweet_text = 'RT from ' + author + ' @' + author_account + '\n\n' + tweet_text tweet_text = 'RT from ' + author + '(@' + author_account + '\n\n)' + tweet_text
# Add footer with link to original tweet # Add footer with link to original tweet
tweet_text += '\n\nOriginal tweet : https://twitter.com' + tweet_id tweet_text += '\n\nOriginal tweet : https://twitter.com/' + tweet_id
# Isolate attached media container # Isolate attached media container
amoc = result.find('div', class_='AdaptiveMediaOuterContainer') amoc = result.find('div', class_='AdaptiveMediaOuterContainer')