Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/streamango.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 compat_chr
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12     js_to_json,
  13 )
  14
  15
  16 class StreamangoIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net|streamcherry\.com)/(?:f|embed)/(?P<id>[^/?#&]+)'
  18     _TESTS = [{
  19         'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
  20         'md5': 'e992787515a182f55e38fc97588d802a',
  21         'info_dict': {
  22             'id': 'clapasobsptpkdfe',
  23             'ext': 'mp4',
  24             'title': '20170315_150006.mp4',
  25         }
  26     }, {
  27         # no og:title
  28         'url': 'https://streamango.com/embed/foqebrpftarclpob/asdf_asd_2_mp4',
  29         'info_dict': {
  30             'id': 'foqebrpftarclpob',
  31             'ext': 'mp4',
  32             'title': 'foqebrpftarclpob',
  33         },
  34         'params': {
  35             'skip_download': True,
  36         },
  37         'skip': 'gone',
  38     }, {
  39         'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
  40         'only_matching': True,
  41     }, {
  42         'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4',
  43         'only_matching': True,
  44     }, {
  45         'url': 'https://streamcherry.com/f/clapasobsptpkdfe/',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_extract(self, url):
  50         def decrypt_src(encoded, val):
  51             ALPHABET = '=/+9876543210zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA'
  52             encoded = re.sub(r'[^A-Za-z0-9+/=]', '', encoded)
  53             decoded = ''
  54             sm = [None] * 4
  55             i = 0
  56             str_len = len(encoded)
  57             while i < str_len:
  58                 for j in range(4):
  59                     sm[j % 4] = ALPHABET.index(encoded[i])
  60                     i += 1
  61                 char_code = ((sm[0] << 0x2) | (sm[1] >> 0x4)) ^ val
  62                 decoded += compat_chr(char_code)
  63                 if sm[2] != 0x40:
  64                     char_code = ((sm[1] & 0xf) << 0x4) | (sm[2] >> 0x2)
  65                     decoded += compat_chr(char_code)
  66                 if sm[3] != 0x40:
  67                     char_code = ((sm[2] & 0x3) << 0x6) | sm[3]
  68                     decoded += compat_chr(char_code)
  69             return decoded
  70
  71         video_id = self._match_id(url)
  72
  73         webpage = self._download_webpage(url, video_id)
  74
  75         title = self._og_search_title(webpage, default=video_id)
  76
  77         formats = []
  78         for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage):
  79             mobj = re.search(r'(src\s*:\s*[^(]+\(([^)]*)\)[\s,]*)', format_)
  80             if mobj is None:
  81                 continue
  82
  83             format_ = format_.replace(mobj.group(0), '')
  84
  85             video = self._parse_json(
  86                 format_, video_id, transform_source=js_to_json,
  87                 fatal=False) or {}
  88
  89             mobj = re.search(
  90                 r'([\'"])(?P<src>(?:(?!\1).)+)\1\s*,\s*(?P<val>\d+)',
  91                 mobj.group(1))
  92             if mobj is None:
  93                 continue
  94
  95             src = decrypt_src(mobj.group('src'), int_or_none(mobj.group('val')))
  96             if not src:
  97                 continue
  98
  99             ext = determine_ext(src, default_ext=None)
 100             if video.get('type') == 'application/dash+xml' or ext == 'mpd':
 101                 formats.extend(self._extract_mpd_formats(
 102                     src, video_id, mpd_id='dash', fatal=False))
 103             else:
 104                 formats.append({
 105                     'url': src,
 106                     'ext': ext or 'mp4',
 107                     'width': int_or_none(video.get('width')),
 108                     'height': int_or_none(video.get('height')),
 109                     'tbr': int_or_none(video.get('bitrate')),
 110                 })
 111
 112         if not formats:
 113             error = self._search_regex(
 114                 r'<p[^>]+\bclass=["\']lead[^>]+>(.+?)</p>', webpage,
 115                 'error', default=None)
 116             if not error and '>Sorry' in webpage:
 117                 error = 'Video %s is not available' % video_id
 118             if error:
 119                 raise ExtractorError(error, expected=True)
 120
 121         self._sort_formats(formats)
 122
 123         return {
 124             'id': video_id,
 125             'url': url,
 126             'title': title,
 127             'formats': formats,
 128         }