Merge tag 'upstream/2017.03.26'

[youtubedl] / youtube_dl / extractor / beeg.py

diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
index 61bc2f7445a6fe115746b8f33b92421c2ab7e32c..b0b7914d89777fcba136a12562f771bf4f2af4d6 100644 (file)
--- a/youtube_dl/extractor/beeg.py
+++ b/youtube_dl/extractor/beeg.py
@@ -1,6 +1,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

+from ..compat import (
+    compat_chr,
+    compat_ord,
+    compat_urllib_parse_unquote,
+)

 from ..utils import (
     int_or_none,
     parse_iso8601,
 from ..utils import (
     int_or_none,
     parse_iso8601,


@@ -28,8 +33,64 @@ class BeegIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

+        webpage = self._download_webpage(url, video_id)
+
+        cpl_url = self._search_regex(
+            r'<script[^>]+src=(["\'])(?P<url>(?:https?:)?//static\.beeg\.com/cpl/\d+\.js.*?)\1',
+            webpage, 'cpl', default=None, group='url')
+
+        beeg_version, beeg_salt = [None] * 2
+
+        if cpl_url:
+            cpl = self._download_webpage(
+                self._proto_relative_url(cpl_url), video_id,
+                'Downloading cpl JS', fatal=False)
+            if cpl:
+                beeg_version = int_or_none(self._search_regex(
+                    r'beeg_version\s*=\s*([^\b]+)', cpl,
+                    'beeg version', default=None)) or self._search_regex(
+                    r'/(\d+)\.js', cpl_url, 'beeg version', default=None)
+                beeg_salt = self._search_regex(
+                    r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt',
+                    default=None, group='beeg_salt')
+
+        beeg_version = beeg_version or '2000'
+        beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
+

         video = self._download_json(
         video = self._download_json(

-            'http://beeg.com/api/v1/video/%s' % video_id, video_id)
+            'https://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
+            video_id)
+
+        def split(o, e):
+            def cut(s, x):
+                n.append(s[:x])
+                return s[x:]
+            n = []
+            r = len(o) % e
+            if r > 0:
+                o = cut(o, r)
+            while len(o) > e:
+                o = cut(o, e)
+            n.append(o)
+            return n
+
+        def decrypt_key(key):
+            # Reverse engineered from http://static.beeg.com/cpl/1738.js
+            a = beeg_salt
+            e = compat_urllib_parse_unquote(key)
+            o = ''.join([
+                compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
+                for n in range(len(e))])
+            return ''.join(split(o, 3)[::-1])
+
+        def decrypt_url(encrypted_url):
+            encrypted_url = self._proto_relative_url(
+                encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
+            key = self._search_regex(
+                r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
+            if not key:
+                return encrypted_url
+            return encrypted_url.replace(key, decrypt_key(key))

 
         formats = []
         for format_id, video_url in video.items():
 
         formats = []
         for format_id, video_url in video.items():


@@ -40,7 +101,7 @@ class BeegIE(InfoExtractor):
             if not height:
                 continue
             formats.append({
             if not height:
                 continue
             formats.append({

-                'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
+                'url': decrypt_url(video_url),

                 'format_id': format_id,
                 'height': int(height),
             })
                 'format_id': format_id,
                 'height': int(height),
             })


@@ -65,5 +126,5 @@ class BeegIE(InfoExtractor):
             'duration': duration,
             'tags': tags,
             'formats': formats,
             'duration': duration,
             'tags': tags,
             'formats': formats,

-            'age_limit': 18,
+            'age_limit': self._rta_search(webpage),

         }
         }