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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_b64decode,
   9     compat_chr,
  10 )
  11 from ..utils import int_or_none
  12
  13
  14 class PopcorntimesIE(InfoExtractor):
  15     _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
  16     _TEST = {
  17         'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy',
  18         'md5': '93f210991ad94ba8c3485950a2453257',
  19         'info_dict': {
  20             'id': 'A1XCFvz',
  21             'display_id': 'haensel-und-gretel-opera-fantasy',
  22             'ext': 'mp4',
  23             'title': 'Hänsel und Gretel',
  24             'description': 'md5:1b8146791726342e7b22ce8125cf6945',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'creator': 'John Paul',
  27             'release_date': '19541009',
  28             'duration': 4260,
  29             'tbr': 5380,
  30             'width': 720,
  31             'height': 540,
  32         },
  33     }
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id, display_id = mobj.group('id', 'display_id')
  38
  39         webpage = self._download_webpage(url, display_id)
  40
  41         title = self._search_regex(
  42             r'<h1>([^<]+)', webpage, 'title',
  43             default=None) or self._html_search_meta(
  44             'ya:ovs:original_name', webpage, 'title', fatal=True)
  45
  46         loc = self._search_regex(
  47             r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc',
  48             group='value')
  49
  50         loc_b64 = ''
  51         for c in loc:
  52             c_ord = ord(c)
  53             if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'):
  54                 upper = ord('Z') if c_ord <= ord('Z') else ord('z')
  55                 c_ord += 13
  56                 if upper < c_ord:
  57                     c_ord -= 26
  58             loc_b64 += compat_chr(c_ord)
  59
  60         video_url = compat_b64decode(loc_b64).decode('utf-8')
  61
  62         description = self._html_search_regex(
  63             r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage,
  64             'description', fatal=False)
  65
  66         thumbnail = self._search_regex(
  67             r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1',
  68             webpage, 'thumbnail', default=None,
  69             group='value') or self._og_search_thumbnail(webpage)
  70
  71         creator = self._html_search_meta(
  72             'video:director', webpage, 'creator', default=None)
  73
  74         release_date = self._html_search_meta(
  75             'video:release_date', webpage, default=None)
  76         if release_date:
  77             release_date = release_date.replace('-', '')
  78
  79         def int_meta(name):
  80             return int_or_none(self._html_search_meta(
  81                 name, webpage, default=None))
  82
  83         return {
  84             'id': video_id,
  85             'display_id': display_id,
  86             'url': video_url,
  87             'title': title,
  88             'description': description,
  89             'thumbnail': thumbnail,
  90             'creator': creator,
  91             'release_date': release_date,
  92             'duration': int_meta('video:duration'),
  93             'tbr': int_meta('ya:ovs:bitrate'),
  94             'width': int_meta('og:video:width'),
  95             'height': int_meta('og:video:height'),
  96             'http_headers': {
  97                 'Referer': url,
  98             },
  99         }