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     determine_ext,
  10     int_or_none,
  11     unified_timestamp,
  12 )
  13
  14
  15 class VineIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
  17     _TESTS = [{
  18         'url': 'https://vine.co/v/b9KOOWX7HUx',
  19         'md5': '2f36fed6235b16da96ce9b4dc890940d',
  20         'info_dict': {
  21             'id': 'b9KOOWX7HUx',
  22             'ext': 'mp4',
  23             'title': 'Chicken.',
  24             'alt_title': 'Vine by Jack',
  25             'timestamp': 1368997951,
  26             'upload_date': '20130519',
  27             'uploader': 'Jack',
  28             'uploader_id': '76',
  29             'view_count': int,
  30             'like_count': int,
  31             'comment_count': int,
  32             'repost_count': int,
  33         },
  34     }, {
  35         'url': 'https://vine.co/v/e192BnZnZ9V',
  36         'info_dict': {
  37             'id': 'e192BnZnZ9V',
  38             'ext': 'mp4',
  39             'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries  #lovesickseason2',
  40             'alt_title': 'Vine by Pimry_zaa',
  41             'timestamp': 1436057405,
  42             'upload_date': '20150705',
  43             'uploader': 'Pimry_zaa',
  44             'uploader_id': '1135760698325307392',
  45             'view_count': int,
  46             'like_count': int,
  47             'comment_count': int,
  48             'repost_count': int,
  49         },
  50         'params': {
  51             'skip_download': True,
  52         },
  53     }, {
  54         'url': 'https://vine.co/v/MYxVapFvz2z',
  55         'only_matching': True,
  56     }, {
  57         'url': 'https://vine.co/v/bxVjBbZlPUH',
  58         'only_matching': True,
  59     }, {
  60         'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66
  67         data = self._download_json(
  68             'https://archive.vine.co/posts/%s.json' % video_id, video_id)
  69
  70         def video_url(kind):
  71             for url_suffix in ('Url', 'URL'):
  72                 format_url = data.get('video%s%s' % (kind, url_suffix))
  73                 if format_url:
  74                     return format_url
  75
  76         formats = []
  77         for quality, format_id in enumerate(('low', '', 'dash')):
  78             format_url = video_url(format_id.capitalize())
  79             if not format_url:
  80                 continue
  81             # DASH link returns plain mp4
  82             if format_id == 'dash' and determine_ext(format_url) == 'mpd':
  83                 formats.extend(self._extract_mpd_formats(
  84                     format_url, video_id, mpd_id='dash', fatal=False))
  85             else:
  86                 formats.append({
  87                     'url': format_url,
  88                     'format_id': format_id or 'standard',
  89                     'quality': quality,
  90                 })
  91         self._sort_formats(formats)
  92
  93         username = data.get('username')
  94
  95         return {
  96             'id': video_id,
  97             'title': data.get('description'),
  98             'alt_title': 'Vine by %s' % username if username else None,
  99             'thumbnail': data.get('thumbnailUrl'),
 100             'timestamp': unified_timestamp(data.get('created')),
 101             'uploader': username,
 102             'uploader_id': data.get('userIdStr'),
 103             'view_count': int_or_none(data.get('loops')),
 104             'like_count': int_or_none(data.get('likes')),
 105             'comment_count': int_or_none(data.get('comments')),
 106             'repost_count': int_or_none(data.get('reposts')),
 107             'formats': formats,
 108         }
 109
 110
 111 class VineUserIE(InfoExtractor):
 112     IE_NAME = 'vine:user'
 113     _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
 114     _VINE_BASE_URL = 'https://vine.co/'
 115     _TESTS = [
 116         {
 117             'url': 'https://vine.co/Visa',
 118             'info_dict': {
 119                 'id': 'Visa',
 120             },
 121             'playlist_mincount': 46,
 122         },
 123         {
 124             'url': 'https://vine.co/u/941705360593584128',
 125             'only_matching': True,
 126         },
 127     ]
 128
 129     def _real_extract(self, url):
 130         mobj = re.match(self._VALID_URL, url)
 131         user = mobj.group('user')
 132         u = mobj.group('u')
 133
 134         profile_url = '%sapi/users/profiles/%s%s' % (
 135             self._VINE_BASE_URL, 'vanity/' if not u else '', user)
 136         profile_data = self._download_json(
 137             profile_url, user, note='Downloading user profile data')
 138
 139         user_id = profile_data['data']['userId']
 140         timeline_data = []
 141         for pagenum in itertools.count(1):
 142             timeline_url = '%sapi/timelines/users/%s?page=%s&size=100' % (
 143                 self._VINE_BASE_URL, user_id, pagenum)
 144             timeline_page = self._download_json(
 145                 timeline_url, user, note='Downloading page %d' % pagenum)
 146             timeline_data.extend(timeline_page['data']['records'])
 147             if timeline_page['data']['nextPage'] is None:
 148                 break
 149
 150         entries = [
 151             self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
 152         return self.playlist_result(entries, user)