Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/patreon.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     clean_html,
   7     determine_ext,
   8     int_or_none,
   9     KNOWN_EXTENSIONS,
  10     mimetype2ext,
  11     parse_iso8601,
  12     str_or_none,
  13     try_get,
  14 )
  15
  16
  17 class PatreonIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)'
  19     _TESTS = [{
  20         'url': 'http://www.patreon.com/creation?hid=743933',
  21         'md5': 'e25505eec1053a6e6813b8ed369875cc',
  22         'info_dict': {
  23             'id': '743933',
  24             'ext': 'mp3',
  25             'title': 'Episode 166: David Smalley of Dogma Debate',
  26             'description': 'md5:713b08b772cd6271b9f3906683cfacdf',
  27             'uploader': 'Cognitive Dissonance Podcast',
  28             'thumbnail': 're:^https?://.*$',
  29             'timestamp': 1406473987,
  30             'upload_date': '20140727',
  31             'uploader_id': '87145',
  32         },
  33     }, {
  34         'url': 'http://www.patreon.com/creation?hid=754133',
  35         'md5': '3eb09345bf44bf60451b8b0b81759d0a',
  36         'info_dict': {
  37             'id': '754133',
  38             'ext': 'mp3',
  39             'title': 'CD 167 Extra',
  40             'uploader': 'Cognitive Dissonance Podcast',
  41             'thumbnail': 're:^https?://.*$',
  42         },
  43         'skip': 'Patron-only content',
  44     }, {
  45         'url': 'https://www.patreon.com/creation?hid=1682498',
  46         'info_dict': {
  47             'id': 'SU4fj_aEMVw',
  48             'ext': 'mp4',
  49             'title': 'I\'m on Patreon!',
  50             'uploader': 'TraciJHines',
  51             'thumbnail': 're:^https?://.*$',
  52             'upload_date': '20150211',
  53             'description': 'md5:c5a706b1f687817a3de09db1eb93acd4',
  54             'uploader_id': 'TraciJHines',
  55         },
  56         'params': {
  57             'noplaylist': True,
  58             'skip_download': True,
  59         }
  60     }, {
  61         'url': 'https://www.patreon.com/posts/episode-166-of-743933',
  62         'only_matching': True,
  63     }, {
  64         'url': 'https://www.patreon.com/posts/743933',
  65         'only_matching': True,
  66     }]
  67
  68     # Currently Patreon exposes download URL via hidden CSS, so login is not
  69     # needed. Keeping this commented for when this inevitably changes.
  70     '''
  71     def _login(self):
  72         username, password = self._get_login_info()
  73         if username is None:
  74             return
  75
  76         login_form = {
  77             'redirectUrl': 'http://www.patreon.com/',
  78             'email': username,
  79             'password': password,
  80         }
  81
  82         request = sanitized_Request(
  83             'https://www.patreon.com/processLogin',
  84             compat_urllib_parse_urlencode(login_form).encode('utf-8')
  85         )
  86         login_page = self._download_webpage(request, None, note='Logging in')
  87
  88         if re.search(r'onLoginFailed', login_page):
  89             raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
  90
  91     def _real_initialize(self):
  92         self._login()
  93     '''
  94
  95     def _real_extract(self, url):
  96         video_id = self._match_id(url)
  97         post = self._download_json(
  98             'https://www.patreon.com/api/posts/' + video_id, video_id, query={
  99                 'fields[media]': 'download_url,mimetype,size_bytes',
 100                 'fields[post]': 'comment_count,content,embed,image,like_count,post_file,published_at,title',
 101                 'fields[user]': 'full_name,url',
 102                 'json-api-use-default-includes': 'false',
 103                 'include': 'media,user',
 104             })
 105         attributes = post['data']['attributes']
 106         title = attributes['title'].strip()
 107         image = attributes.get('image') or {}
 108         info = {
 109             'id': video_id,
 110             'title': title,
 111             'description': clean_html(attributes.get('content')),
 112             'thumbnail': image.get('large_url') or image.get('url'),
 113             'timestamp': parse_iso8601(attributes.get('published_at')),
 114             'like_count': int_or_none(attributes.get('like_count')),
 115             'comment_count': int_or_none(attributes.get('comment_count')),
 116         }
 117
 118         for i in post.get('included', []):
 119             i_type = i.get('type')
 120             if i_type == 'media':
 121                 media_attributes = i.get('attributes') or {}
 122                 download_url = media_attributes.get('download_url')
 123                 ext = mimetype2ext(media_attributes.get('mimetype'))
 124                 if download_url and ext in KNOWN_EXTENSIONS:
 125                     info.update({
 126                         'ext': ext,
 127                         'filesize': int_or_none(media_attributes.get('size_bytes')),
 128                         'url': download_url,
 129                     })
 130             elif i_type == 'user':
 131                 user_attributes = i.get('attributes')
 132                 if user_attributes:
 133                     info.update({
 134                         'uploader': user_attributes.get('full_name'),
 135                         'uploader_id': str_or_none(i.get('id')),
 136                         'uploader_url': user_attributes.get('url'),
 137                     })
 138
 139         if not info.get('url'):
 140             embed_url = try_get(attributes, lambda x: x['embed']['url'])
 141             if embed_url:
 142                 info.update({
 143                     '_type': 'url',
 144                     'url': embed_url,
 145                 })
 146
 147         if not info.get('url'):
 148             post_file = attributes['post_file']
 149             ext = determine_ext(post_file.get('name'))
 150             if ext in KNOWN_EXTENSIONS:
 151                 info.update({
 152                     'ext': ext,
 153                     'url': post_file['url'],
 154                 })
 155
 156         return info