github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[twitter] Simplify and improve

Browse source
This commit is contained in:
Yen Chi Hsuan 2015-10-18 18:04:13 +08:00
parent f6dfd6603a
commit 575036b405
1 changed files with 24 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
youtube_dl/extractor/twitter.py
View file

@ -9,6 +9,7 @@
float_or_none, float_or_none,
unescapeHTML, unescapeHTML,
xpath_text, xpath_text,
remove_end,
) )
@ -99,7 +100,8 @@ def _real_extract(self, url):
class TwitterIE(InfoExtractor): class TwitterIE(InfoExtractor):
IE_NAME = 'twitter' IE_NAME = 'twitter'
_VALID_URL = r'https?://(?:www|m|mobile)?\.?twitter\.com/(?P<id>[^/]+/status/\d+)' _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
_TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
_TEST = { _TEST = {
'url': 'https://twitter.com/freethenipple/status/643211948184596480', 'url': 'https://twitter.com/freethenipple/status/643211948184596480',
@ -107,7 +109,7 @@ class TwitterIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '643211948184596480', 'id': '643211948184596480',
'ext': 'mp4', 'ext': 'mp4',
'title': 'freethenipple - FTN supporters on Hollywood Blvd today!', 'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
'thumbnail': 're:^https?://.*\.jpg', 'thumbnail': 're:^https?://.*\.jpg',
'duration': 12.922, 'duration': 12.922,
'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"', 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
@ -117,26 +119,31 @@ class TwitterIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
username, twid = re.match(r'([^/]+)/status/(\d+)', id).groups() user_id = mobj.group('user_id')
name = username twid = mobj.group('id')
url = re.sub(r'https?://(m|mobile)\.', 'https://', url)
webpage = self._download_webpage(url, 'tweet: ' + url) webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)
description = self._html_search_regex('<title>\s*(.+?)\s*</title>', webpage, 'title')
title = description.replace('\n', ' ') username = remove_end(self._og_search_title(webpage), ' on Twitter')
splitdesc = re.match(r'^(.+?)\s*on Twitter:\s* "(.+?)"$', title)
if splitdesc: title = self._og_search_description(webpage).strip('').replace('\n', ' ')
name, title = splitdesc.groups()
title = re.sub(r'\s*https?://[^ ]+', '', title) # strip 'https -_t.co_BJYgOjSeGA' junk from filenames # strip 'https -_t.co_BJYgOjSeGA' junk from filenames
card_id = self._search_regex(r'["\']/i/cards/tfw/v1/(\d+)', webpage, '/i/card/...') mobj = re.match(r'“(.*)\s+(http://[^ ]+)”', title)
title, short_url = mobj.groups()
card_id = self._search_regex(
r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url')
card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'ie_key': 'TwitterCard', 'ie_key': 'TwitterCard',
'uploader_id': username, 'uploader_id': user_id,
'uploader': name, 'uploader': username,
'url': card_url, 'url': card_url,
'webpage_url': url, 'webpage_url': url,
'description': description, 'description': '%s on Twitter: "%s %s"' % (username, title, short_url),
'title': username + ' - ' + title, 'title': username + ' - ' + title,
} }