youtube_dl/extractor/vine.py

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