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