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             'format_id': '%(format)s-%(rate)s' % f,
  37             'vcodec': f['format'],
  38             'quality': f['rate'],
  39             'url': f['videoUrl'],
  40         } for f in data['videoUrls']]
  41
  42         self._sort_formats(formats)
  43
  44         return {
  45             'id': video_id,
  46             'title': self._og_search_title(webpage),
  47             'alt_title': self._og_search_description(webpage),
  48             'description': data['description'],
  49             'thumbnail': data['thumbnailUrl'],
  50             'upload_date': unified_strdate(data['created']),
  51             'uploader': data['username'],
  52             'uploader_id': data['userIdStr'],
  53             'like_count': data['likes']['count'],
  54             'comment_count': data['comments']['count'],
  55             'repost_count': data['reposts']['count'],
  56             'formats': formats,
  57         }
  58
  59
  60 class VineUserIE(InfoExtractor):
  61     IE_NAME = 'vine:user'
  62     _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
  63     _VINE_BASE_URL = "https://vine.co/"
  64     _TESTS = [
  65         {
  66             'url': 'https://vine.co/Visa',
  67             'info_dict': {
  68                 'id': 'Visa',
  69             },
  70             'playlist_mincount': 46,
  71         },
  72         {
  73             'url': 'https://vine.co/u/941705360593584128',
  74             'only_matching': True,
  75         },
  76     ]
  77
  78     def _real_extract(self, url):
  79         mobj = re.match(self._VALID_URL, url)
  80         user = mobj.group('user')
  81         u = mobj.group('u')
  82
  83         profile_url = "%sapi/users/profiles/%s%s" % (
  84             self._VINE_BASE_URL, 'vanity/' if not u else '', user)
  85         profile_data = self._download_json(
  86             profile_url, user, note='Downloading user profile data')
  87
  88         user_id = profile_data['data']['userId']
  89         timeline_data = []
  90         for pagenum in itertools.count(1):
  91             timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % (
  92                 self._VINE_BASE_URL, user_id, pagenum)
  93             timeline_page = self._download_json(
  94                 timeline_url, user, note='Downloading page %d' % pagenum)
  95             timeline_data.extend(timeline_page['data']['records'])
  96             if timeline_page['data']['nextPage'] is None:
  97                 break
  98
  99         entries = [
 100             self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
 101         return self.playlist_result(entries, user)