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             'view_count': int,
  28             'like_count': int,
  29             'comment_count': int,
  30             'repost_count': int,
  31         },
  32     }, {
  33         'url': 'https://vine.co/v/MYxVapFvz2z',
  34         'md5': '7b9a7cbc76734424ff942eb52c8f1065',
  35         'info_dict': {
  36             'id': 'MYxVapFvz2z',
  37             'ext': 'mp4',
  38             'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
  39             'alt_title': 'Vine by Mars Ruiz',
  40             'upload_date': '20140815',
  41             'uploader': 'Mars Ruiz',
  42             'uploader_id': '1102363502380728320',
  43             'view_count': int,
  44             'like_count': int,
  45             'comment_count': int,
  46             'repost_count': int,
  47         },
  48     }, {
  49         'url': 'https://vine.co/v/bxVjBbZlPUH',
  50         'md5': 'ea27decea3fa670625aac92771a96b73',
  51         'info_dict': {
  52             'id': 'bxVjBbZlPUH',
  53             'ext': 'mp4',
  54             'title': '#mw3 #ac130 #killcam #angelofdeath',
  55             'alt_title': 'Vine by Z3k3',
  56             'upload_date': '20130430',
  57             'uploader': 'Z3k3',
  58             'uploader_id': '936470460173008896',
  59             'view_count': int,
  60             'like_count': int,
  61             'comment_count': int,
  62             'repost_count': int,
  63         },
  64     }, {
  65         'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
  66         'only_matching': True,
  67     }, {
  68         'url': 'https://vine.co/v/e192BnZnZ9V',
  69         'info_dict': {
  70             'id': 'e192BnZnZ9V',
  71             'ext': 'mp4',
  72             'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries  #lovesickseason2',
  73             'alt_title': 'Vine by Pimry_zaa',
  74             'upload_date': '20150705',
  75             'uploader': 'Pimry_zaa',
  76             'uploader_id': '1135760698325307392',
  77             'view_count': int,
  78             'like_count': int,
  79             'comment_count': int,
  80             'repost_count': int,
  81         },
  82         'params': {
  83             'skip_download': True,
  84         },
  85     }]
  86
  87     def _real_extract(self, url):
  88         video_id = self._match_id(url)
  89         webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
  90
  91         data = self._parse_json(
  92             self._search_regex(
  93                 r'window\.POST_DATA\s*=\s*{\s*%s\s*:\s*({.+?})\s*};\s*</script>' % video_id,
  94                 webpage, 'vine data'),
  95             video_id)
  96
  97         formats = [{
  98             'format_id': '%(format)s-%(rate)s' % f,
  99             'vcodec': f.get('format'),
 100             'quality': f.get('rate'),
 101             'url': f['videoUrl'],
 102         } for f in data['videoUrls'] if f.get('videoUrl')]
 103
 104         self._sort_formats(formats)
 105
 106         username = data.get('username')
 107
 108         return {
 109             'id': video_id,
 110             'title': data.get('description') or self._og_search_title(webpage),
 111             'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None),
 112             'thumbnail': data.get('thumbnailUrl'),
 113             'upload_date': unified_strdate(data.get('created')),
 114             'uploader': username,
 115             'uploader_id': data.get('userIdStr'),
 116             'view_count': int_or_none(data.get('loops', {}).get('count')),
 117             'like_count': int_or_none(data.get('likes', {}).get('count')),
 118             'comment_count': int_or_none(data.get('comments', {}).get('count')),
 119             'repost_count': int_or_none(data.get('reposts', {}).get('count')),
 120             'formats': formats,
 121         }
 122
 123
 124 class VineUserIE(InfoExtractor):
 125     IE_NAME = 'vine:user'
 126     _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
 127     _VINE_BASE_URL = 'https://vine.co/'
 128     _TESTS = [
 129         {
 130             'url': 'https://vine.co/Visa',
 131             'info_dict': {
 132                 'id': 'Visa',
 133             },
 134             'playlist_mincount': 46,
 135         },
 136         {
 137             'url': 'https://vine.co/u/941705360593584128',
 138             'only_matching': True,
 139         },
 140     ]
 141
 142     def _real_extract(self, url):
 143         mobj = re.match(self._VALID_URL, url)
 144         user = mobj.group('user')
 145         u = mobj.group('u')
 146
 147         profile_url = '%sapi/users/profiles/%s%s' % (
 148             self._VINE_BASE_URL, 'vanity/' if not u else '', user)
 149         profile_data = self._download_json(
 150             profile_url, user, note='Downloading user profile data')
 151
 152         user_id = profile_data['data']['userId']
 153         timeline_data = []
 154         for pagenum in itertools.count(1):
 155             timeline_url = '%sapi/timelines/users/%s?page=%s&size=100' % (
 156                 self._VINE_BASE_URL, user_id, pagenum)
 157             timeline_page = self._download_json(
 158                 timeline_url, user, note='Downloading page %d' % pagenum)
 159             timeline_data.extend(timeline_page['data']['records'])
 160             if timeline_page['data']['nextPage'] is None:
 161                 break
 162
 163         entries = [
 164             self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
 165         return self.playlist_result(entries, user)