yt_dlp/extractor/playplustv.py

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