PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-23 21:45:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[twitter] fix #2609

Browse Source
This commit is contained in:
Mort Yao 2018-08-08 16:21:49 +02:00
parent f73c7a3660
commit da8c982608
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 17 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
src/you_get/extractors/twitter.py
View File

@ -64,42 +64,26 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
output_dir=output_dir)
except: # extract video
# always use i/cards or videos url
if not re.match(r'https?://twitter.com/i/', url):
url = r1(r'<meta\s*property="og:video:url"\s*content="([^"]+)"', html)
if not url:
url = 'https://twitter.com/i/videos/%s' % item_id
try:
html = get_content(url)
except:
return
#i_url = 'https://twitter.com/i/videos/' + item_id
#i_content = get_content(i_url)
#js_url = r1(r'src="([^"]+)"', i_content)
#js_content = get_content(js_url)
#authorization = r1(r'"(Bearer [^"]+)"', js_content)
authorization = 'Bearer AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA'
data_config = r1(r'data-config="([^"]*)"', html) or \
r1(r'data-player-config="([^"]*)"', html)
i = json.loads(unescape_html(data_config))
if 'video_url' in i:
source = i['video_url']
item_id = i['tweet_id']
page_title = "{} [{}]".format(screen_name, item_id)
elif 'playlist' in i:
source = i['playlist'][0]['source']
if not item_id: page_title = i['playlist'][0]['contentId']
elif 'vmap_url' in i:
vmap_url = i['vmap_url']
vmap = get_content(vmap_url)
source = r1(r'<MediaFile>\s*<!\[CDATA\[(.*)\]\]>', vmap)
item_id = i['tweet_id']
page_title = "{} [{}]".format(screen_name, item_id)
elif 'scribe_playlist_url' in i:
scribe_playlist_url = i['scribe_playlist_url']
return vine_download(scribe_playlist_url, output_dir, merge=merge, info_only=info_only)
ga_url = 'https://api.twitter.com/1.1/guest/activate.json'
ga_content = post_content(ga_url, headers={'authorization': authorization})
guest_token = json.loads(ga_content)['guest_token']
try:
urls = extract_m3u(source)
except:
urls = [source]
api_url = 'https://api.twitter.com/2/timeline/conversation/%s.json?tweet_mode=extended' % item_id
api_content = get_content(api_url, headers={'authorization': authorization, 'x-guest-token': guest_token})
info = json.loads(api_content)
variants = info['globalObjects']['tweets'][item_id]['extended_entities']['media'][0]['video_info']['variants']
variants = sorted(variants, key=lambda kv: kv.get('bitrate', 0))
urls = [ variants[-1]['url'] ]
size = urls_size(urls)
mime, ext = 'video/mp4', 'mp4'
mime, ext = variants[-1]['content_type'], 'mp4'
print_info(site_info, page_title, mime, size)
if not info_only: