_ Git - youtube-dl/blob - youtube_dl/extractor/playplustv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_HTTPError
   9 from ..utils import (
  10     clean_html,
  11     ExtractorError,
  12     int_or_none,
  13     PUTRequest,
  14 )
  15
  16
  17 class PlayPlusTVIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?playplus\.(?:com|tv)/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})'
  19     _TEST = {
  20         'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e',
  21         'md5': 'd078cb89d7ab6b9df37ce23c647aef72',
  22         'info_dict': {
  23             'id': 'db8d274a5163424e967f35a30ddafb8e',
  24             'ext': 'mp4',
  25             'title': 'Capítulo 179 - Final',
  26             'description': 'md5:01085d62d8033a1e34121d3c3cabc838',
  27             'timestamp': 1529992740,
  28             'upload_date': '20180626',
  29         },
  30         'skip': 'Requires account credential',
  31     }
  32     _NETRC_MACHINE = 'playplustv'
  33     _GEO_COUNTRIES = ['BR']
  34     _token = None
  35     _profile_id = None
  36
  37     def _call_api(self, resource, video_id=None, query=None):
  38         return self._download_json('https://api.playplus.tv/api/media/v2/get' + resource, video_id, headers={
  39             'Authorization': 'Bearer ' + self._token,
  40         }, query=query)
  41
  42     def _real_initialize(self):
  43         email, password = self._get_login_info()
  44         if email is None:
  45             self.raise_login_required()
  46
  47         req = PUTRequest(
  48             'https://api.playplus.tv/api/web/login', json.dumps({
  49                 'email': email,
  50                 'password': password,
  51             }).encode(), {
  52                 'Content-Type': 'application/json; charset=utf-8',
  53             })
  54
  55         try:
  56             self._token = self._download_json(req, None)['token']
  57         except ExtractorError as e:
  58             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
  59                 raise ExtractorError(self._parse_json(
  60                     e.cause.read(), None)['errorMessage'], expected=True)
  61             raise
  62
  63         self._profile = self._call_api('Profiles')['list'][0]['_id']
  64
  65     def _real_extract(self, url):
  66         project_id, media_id = re.match(self._VALID_URL, url).groups()
  67         media = self._call_api(
  68             'Media', media_id, {
  69                 'profileId': self._profile,
  70                 'projectId': project_id,
  71                 'mediaId': media_id,
  72             })['obj']
  73         title = media['title']
  74
  75         formats = []
  76         for f in media.get('files', []):
  77             f_url = f.get('url')
  78             if not f_url:
  79                 continue
  80             file_info = f.get('fileInfo') or {}
  81             formats.append({
  82                 'url': f_url,
  83                 'width': int_or_none(file_info.get('width')),
  84                 'height': int_or_none(file_info.get('height')),
  85             })
  86         self._sort_formats(formats)
  87
  88         thumbnails = []
  89         for thumb in media.get('thumbs', []):
  90             thumb_url = thumb.get('url')
  91             if not thumb_url:
  92                 continue
  93             thumbnails.append({
  94                 'url': thumb_url,
  95                 'width': int_or_none(thumb.get('width')),
  96                 'height': int_or_none(thumb.get('height')),
  97             })
  98
  99         return {
 100             'id': media_id,
 101             'title': title,
 102             'formats': formats,
 103             'thumbnails': thumbnails,
 104             'description': clean_html(media.get('description')) or media.get('shortDescription'),
 105             'timestamp': int_or_none(media.get('publishDate'), 1000),
 106             'view_count': int_or_none(media.get('numberOfViews')),
 107             'comment_count': int_or_none(media.get('numberOfComments')),
 108             'tags': media.get('tags'),
 109         }