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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import itertools
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     int_or_none,
  10     unified_strdate,
  11 )
  12
  13
  14 class VineIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
  16     _TESTS = [{
  17         'url': 'https://vine.co/v/b9KOOWX7HUx',
  18         'md5': '2f36fed6235b16da96ce9b4dc890940d',
  19         'info_dict': {
  20             'id': 'b9KOOWX7HUx',
  21             'ext': 'mp4',
  22             'title': 'Chicken.',
  23             'alt_title': 'Vine by Jack Dorsey',
  24             'upload_date': '20130519',
  25             'uploader': 'Jack Dorsey',
  26             'uploader_id': '76',
  27             'like_count': int,
  28             'comment_count': int,
  29             'repost_count': int,
  30         },
  31     }, {
  32         'url': 'https://vine.co/v/MYxVapFvz2z',
  33         'md5': '7b9a7cbc76734424ff942eb52c8f1065',
  34         'info_dict': {
  35             'id': 'MYxVapFvz2z',
  36             'ext': 'mp4',
  37             'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
  38             'alt_title': 'Vine by Mars Ruiz',
  39             'upload_date': '20140815',
  40             'uploader': 'Mars Ruiz',
  41             'uploader_id': '1102363502380728320',
  42             'like_count': int,
  43             'comment_count': int,
  44             'repost_count': int,
  45         },
  46     }, {
  47         'url': 'https://vine.co/v/bxVjBbZlPUH',
  48         'md5': 'ea27decea3fa670625aac92771a96b73',
  49         'info_dict': {
  50             'id': 'bxVjBbZlPUH',
  51             'ext': 'mp4',
  52             'title': '#mw3 #ac130 #killcam #angelofdeath',
  53             'alt_title': 'Vine by Z3k3',
  54             'upload_date': '20130430',
  55             'uploader': 'Z3k3',
  56             'uploader_id': '936470460173008896',
  57             'like_count': int,
  58             'comment_count': int,
  59             'repost_count': int,
  60         },
  61     }, {
  62         'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
  63         'only_matching': True,
  64     }, {
  65         'url': 'https://vine.co/v/e192BnZnZ9V',
  66         'info_dict': {
  67             'id': 'e192BnZnZ9V',
  68             'ext': 'mp4',
  69             'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries  #lovesickseason2',
  70             'alt_title': 'Vine by Pimry_zaa',
  71             'upload_date': '20150705',
  72             'uploader': 'Pimry_zaa',
  73             'uploader_id': '1135760698325307392',
  74             'like_count': int,
  75             'comment_count': int,
  76             'repost_count': int,
  77         },
  78         'params': {
  79             'skip_download': True,
  80         },
  81     }]
  82
  83     def _real_extract(self, url):
  84         video_id = self._match_id(url)
  85         webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
  86
  87         data = self._parse_json(
  88             self._search_regex(
  89                 r'window\.POST_DATA\s*=\s*{\s*%s\s*:\s*({.+?})\s*};\s*</script>' % video_id,
  90                 webpage, 'vine data'),
  91             video_id)
  92
  93         formats = [{
  94             'format_id': '%(format)s-%(rate)s' % f,
  95             'vcodec': f.get('format'),
  96             'quality': f.get('rate'),
  97             'url': f['videoUrl'],
  98         } for f in data['videoUrls'] if f.get('videoUrl')]
  99
 100         self._sort_formats(formats)
 101
 102         username = data.get('username')
 103
 104         return {
 105             'id': video_id,
 106             'title': data.get('description') or self._og_search_title(webpage),
 107             'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None),
 108             'thumbnail': data.get('thumbnailUrl'),
 109             'upload_date': unified_strdate(data.get('created')),
 110             'uploader': username,
 111             'uploader_id': data.get('userIdStr'),
 112             'like_count': int_or_none(data.get('likes', {}).get('count')),
 113             'comment_count': int_or_none(data.get('comments', {}).get('count')),
 114             'repost_count': int_or_none(data.get('reposts', {}).get('count')),
 115             'formats': formats,
 116         }
 117
 118
 119 class VineUserIE(InfoExtractor):
 120     IE_NAME = 'vine:user'
 121     _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
 122     _VINE_BASE_URL = 'https://vine.co/'
 123     _TESTS = [
 124         {
 125             'url': 'https://vine.co/Visa',
 126             'info_dict': {
 127                 'id': 'Visa',
 128             },
 129             'playlist_mincount': 46,
 130         },
 131         {
 132             'url': 'https://vine.co/u/941705360593584128',
 133             'only_matching': True,
 134         },
 135     ]
 136
 137     def _real_extract(self, url):
 138         mobj = re.match(self._VALID_URL, url)
 139         user = mobj.group('user')
 140         u = mobj.group('u')
 141
 142         profile_url = '%sapi/users/profiles/%s%s' % (
 143             self._VINE_BASE_URL, 'vanity/' if not u else '', user)
 144         profile_data = self._download_json(
 145             profile_url, user, note='Downloading user profile data')
 146
 147         user_id = profile_data['data']['userId']
 148         timeline_data = []
 149         for pagenum in itertools.count(1):
 150             timeline_url = '%sapi/timelines/users/%s?page=%s&size=100' % (
 151                 self._VINE_BASE_URL, user_id, pagenum)
 152             timeline_page = self._download_json(
 153                 timeline_url, user, note='Downloading page %d' % pagenum)
 154             timeline_data.extend(timeline_page['data']['records'])
 155             if timeline_page['data']['nextPage'] is None:
 156                 break
 157
 158         entries = [
 159             self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
 160         return self.playlist_result(entries, user)