Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vine.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import itertools
   5
   6 from .common import InfoExtractor
   7 from ..utils import unified_strdate
   8
   9
  10 class VineIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
  12     _TESTS = [{
  13         'url': 'https://vine.co/v/b9KOOWX7HUx',
  14         'md5': '2f36fed6235b16da96ce9b4dc890940d',
  15         'info_dict': {
  16             'id': 'b9KOOWX7HUx',
  17             'ext': 'mp4',
  18             'title': 'Chicken.',
  19             'alt_title': 'Vine by Jack Dorsey',
  20             'description': 'Chicken.',
  21             'upload_date': '20130519',
  22             'uploader': 'Jack Dorsey',
  23             'uploader_id': '76',
  24         },
  25     }, {
  26         'url': 'https://vine.co/v/MYxVapFvz2z',
  27         'md5': '7b9a7cbc76734424ff942eb52c8f1065',
  28         'info_dict': {
  29             'id': 'MYxVapFvz2z',
  30             'ext': 'mp4',
  31             'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
  32             'alt_title': 'Vine by Luna',
  33             'description': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
  34             'upload_date': '20140815',
  35             'uploader': 'Luna',
  36             'uploader_id': '1102363502380728320',
  37         },
  38     }, {
  39         'url': 'https://vine.co/v/bxVjBbZlPUH',
  40         'md5': 'ea27decea3fa670625aac92771a96b73',
  41         'info_dict': {
  42             'id': 'bxVjBbZlPUH',
  43             'ext': 'mp4',
  44             'title': '#mw3 #ac130 #killcam #angelofdeath',
  45             'alt_title': 'Vine by Z3k3',
  46             'description': '#mw3 #ac130 #killcam #angelofdeath',
  47             'upload_date': '20130430',
  48             'uploader': 'Z3k3',
  49             'uploader_id': '936470460173008896',
  50         },
  51     }, {
  52         'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
  53         'only_matching': True,
  54     }]
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58         webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
  59
  60         data = self._parse_json(
  61             self._html_search_regex(
  62                 r'window\.POST_DATA = { %s: ({.+?}) };\s*</script>' % video_id,
  63                 webpage, 'vine data'),
  64             video_id)
  65
  66         formats = [{
  67             'format_id': '%(format)s-%(rate)s' % f,
  68             'vcodec': f['format'],
  69             'quality': f['rate'],
  70             'url': f['videoUrl'],
  71         } for f in data['videoUrls']]
  72
  73         self._sort_formats(formats)
  74
  75         return {
  76             'id': video_id,
  77             'title': self._og_search_title(webpage),
  78             'alt_title': self._og_search_description(webpage, default=None),
  79             'description': data['description'],
  80             'thumbnail': data['thumbnailUrl'],
  81             'upload_date': unified_strdate(data['created']),
  82             'uploader': data['username'],
  83             'uploader_id': data['userIdStr'],
  84             'like_count': data['likes']['count'],
  85             'comment_count': data['comments']['count'],
  86             'repost_count': data['reposts']['count'],
  87             'formats': formats,
  88         }
  89
  90
  91 class VineUserIE(InfoExtractor):
  92     IE_NAME = 'vine:user'
  93     _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
  94     _VINE_BASE_URL = "https://vine.co/"
  95     _TESTS = [
  96         {
  97             'url': 'https://vine.co/Visa',
  98             'info_dict': {
  99                 'id': 'Visa',
 100             },
 101             'playlist_mincount': 46,
 102         },
 103         {
 104             'url': 'https://vine.co/u/941705360593584128',
 105             'only_matching': True,
 106         },
 107     ]
 108
 109     def _real_extract(self, url):
 110         mobj = re.match(self._VALID_URL, url)
 111         user = mobj.group('user')
 112         u = mobj.group('u')
 113
 114         profile_url = "%sapi/users/profiles/%s%s" % (
 115             self._VINE_BASE_URL, 'vanity/' if not u else '', user)
 116         profile_data = self._download_json(
 117             profile_url, user, note='Downloading user profile data')
 118
 119         user_id = profile_data['data']['userId']
 120         timeline_data = []
 121         for pagenum in itertools.count(1):
 122             timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % (
 123                 self._VINE_BASE_URL, user_id, pagenum)
 124             timeline_page = self._download_json(
 125                 timeline_url, user, note='Downloading page %d' % pagenum)
 126             timeline_data.extend(timeline_page['data']['records'])
 127             if timeline_page['data']['nextPage'] is None:
 128                 break
 129
 130         entries = [
 131             self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
 132         return self.playlist_result(entries, user)