_ Git - youtube-dl/blob - 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/(?P<id>\w+)'
  13     _TEST = {
  14         'url': 'https://vine.co/v/b9KOOWX7HUx',
  15         'md5': '2f36fed6235b16da96ce9b4dc890940d',
  16         'info_dict': {
  17             'id': 'b9KOOWX7HUx',
  18             'ext': 'mp4',
  19             'title': 'Chicken.',
  20             'description': 'Chicken.',
  21             'upload_date': '20130519',
  22             'uploader': 'Jack Dorsey',
  23             'uploader_id': '76',
  24         },
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
  32
  33         data = json.loads(self._html_search_regex(
  34             r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
  35
  36         formats = [
  37             {
  38                 'url': data['videoLowURL'],
  39                 'ext': 'mp4',
  40                 'format_id': 'low',
  41             },
  42             {
  43                 'url': data['videoUrl'],
  44                 'ext': 'mp4',
  45                 'format_id': 'standard',
  46             }
  47         ]
  48
  49         return {
  50             'id': video_id,
  51             'title': self._og_search_title(webpage),
  52             'description': data['description'],
  53             'thumbnail': data['thumbnailUrl'],
  54             'upload_date': unified_strdate(data['created']),
  55             'uploader': data['username'],
  56             'uploader_id': data['userIdStr'],
  57             'like_count': data['likes']['count'],
  58             'comment_count': data['comments']['count'],
  59             'repost_count': data['reposts']['count'],
  60             'formats': formats,
  61         }
  62
  63
  64 class VineUserIE(InfoExtractor):
  65     IE_NAME = 'vine:user'
  66     _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
  67     _VINE_BASE_URL = "https://vine.co/"
  68     _TESTS = [
  69         {
  70             'url': 'https://vine.co/Visa',
  71             'info_dict': {
  72                 'id': 'Visa',
  73             },
  74             'playlist_mincount': 46,
  75         },
  76         {
  77             'url': 'https://vine.co/u/941705360593584128',
  78             'only_matching': True,
  79         },
  80     ]
  81
  82     def _real_extract(self, url):
  83         mobj = re.match(self._VALID_URL, url)
  84         user = mobj.group('user')
  85         u = mobj.group('u')
  86
  87         profile_url = "%sapi/users/profiles/%s%s" % (
  88             self._VINE_BASE_URL, 'vanity/' if not u else '', user)
  89         profile_data = self._download_json(
  90             profile_url, user, note='Downloading user profile data')
  91
  92         user_id = profile_data['data']['userId']
  93         timeline_data = []
  94         for pagenum in itertools.count(1):
  95             timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % (
  96                 self._VINE_BASE_URL, user_id, pagenum)
  97             timeline_page = self._download_json(
  98                 timeline_url, user, note='Downloading page %d' % pagenum)
  99             timeline_data.extend(timeline_page['data']['records'])
 100             if timeline_page['data']['nextPage'] is None:
 101                 break
 102
 103         entries = [
 104             self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
 105         return self.playlist_result(entries, user)