]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/streamango.py
debian/control: State compliancy with Debian Policy 4.4.0.
[youtubedl] / youtube_dl / extractor / streamango.py
index a9e34c027504ff0f6585fa51cae4ba3a1ec5bfcd..f1e17dd887f8a4ab010ff1b406087da5ba6af676 100644 (file)
@@ -4,15 +4,17 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_chr
 from ..utils import (
     determine_ext,
+    ExtractorError,
     int_or_none,
     js_to_json,
 )
 
 
 class StreamangoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net|streamcherry\.com)/(?:f|embed)/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
         'md5': 'e992787515a182f55e38fc97588d802a',
@@ -32,12 +34,40 @@ class StreamangoIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'gone',
     }, {
         'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
         'only_matching': True,
+    }, {
+        'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4',
+        'only_matching': True,
+    }, {
+        'url': 'https://streamcherry.com/f/clapasobsptpkdfe/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
+        def decrypt_src(encoded, val):
+            ALPHABET = '=/+9876543210zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA'
+            encoded = re.sub(r'[^A-Za-z0-9+/=]', '', encoded)
+            decoded = ''
+            sm = [None] * 4
+            i = 0
+            str_len = len(encoded)
+            while i < str_len:
+                for j in range(4):
+                    sm[j % 4] = ALPHABET.index(encoded[i])
+                    i += 1
+                char_code = ((sm[0] << 0x2) | (sm[1] >> 0x4)) ^ val
+                decoded += compat_chr(char_code)
+                if sm[2] != 0x40:
+                    char_code = ((sm[1] & 0xf) << 0x4) | (sm[2] >> 0x2)
+                    decoded += compat_chr(char_code)
+                if sm[3] != 0x40:
+                    char_code = ((sm[2] & 0x3) << 0x6) | sm[3]
+                    decoded += compat_chr(char_code)
+            return decoded
+
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
@@ -46,13 +76,26 @@ class StreamangoIE(InfoExtractor):
 
         formats = []
         for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage):
+            mobj = re.search(r'(src\s*:\s*[^(]+\(([^)]*)\)[\s,]*)', format_)
+            if mobj is None:
+                continue
+
+            format_ = format_.replace(mobj.group(0), '')
+
             video = self._parse_json(
-                format_, video_id, transform_source=js_to_json, fatal=False)
-            if not video:
+                format_, video_id, transform_source=js_to_json,
+                fatal=False) or {}
+
+            mobj = re.search(
+                r'([\'"])(?P<src>(?:(?!\1).)+)\1\s*,\s*(?P<val>\d+)',
+                mobj.group(1))
+            if mobj is None:
                 continue
-            src = video.get('src')
+
+            src = decrypt_src(mobj.group('src'), int_or_none(mobj.group('val')))
             if not src:
                 continue
+
             ext = determine_ext(src, default_ext=None)
             if video.get('type') == 'application/dash+xml' or ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
@@ -65,6 +108,16 @@ class StreamangoIE(InfoExtractor):
                     'height': int_or_none(video.get('height')),
                     'tbr': int_or_none(video.get('bitrate')),
                 })
+
+        if not formats:
+            error = self._search_regex(
+                r'<p[^>]+\bclass=["\']lead[^>]+>(.+?)</p>', webpage,
+                'error', default=None)
+            if not error and '>Sorry' in webpage:
+                error = 'Video %s is not available' % video_id
+            if error:
+                raise ExtractorError(error, expected=True)
+
         self._sort_formats(formats)
 
         return {