debian/control: Update list of extractors in long description.

[youtubedl] / youtube_dl / extractor / beeg.py

diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
index 34c2a756fba11f81516e87e095ef1e02d5e65417..bf22a41b745db2eef277c6fc41cf716cef6d6366 100644 (file)
--- a/youtube_dl/extractor/beeg.py
+++ b/youtube_dl/extractor/beeg.py
@@ -9,6 +9,7 @@ from ..compat import (
 from ..utils import (
     int_or_none,
     parse_iso8601,
 from ..utils import (
     int_or_none,
     parse_iso8601,

+    urljoin,

 )
 
 
 )
 
 


@@ -16,7 +17,7 @@ class BeegIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
     _TEST = {
         'url': 'http://beeg.com/5416503',
     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
     _TEST = {
         'url': 'http://beeg.com/5416503',

-        'md5': '46c384def73b33dbc581262e5ee67cef',
+        'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',

         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',


@@ -33,8 +34,39 @@ 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)
 

-        video = self._download_json(
-            'https://api.beeg.com/api/v5/video/%s' % video_id, video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        cpl_url = self._search_regex(
+            r'<script[^>]+src=(["\'])(?P<url>(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1',
+            webpage, 'cpl', default=None, group='url')
+
+        cpl_url = urljoin(url, cpl_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 '2185'
+        beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
+
+        for api_path in ('', 'api.'):
+            video = self._download_json(
+                'https://%sbeeg.com/api/v6/%s/video/%s'
+                % (api_path, beeg_version, video_id), video_id,
+                fatal=api_path == 'api.')
+            if video:
+                break

 
         def split(o, e):
             def cut(s, x):
 
         def split(o, e):
             def cut(s, x):


@@ -50,8 +82,8 @@ class BeegIE(InfoExtractor):
             return n
 
         def decrypt_key(key):
             return n
 
         def decrypt_key(key):

-            # Reverse engineered from http://static.beeg.com/cpl/1105.js
-            a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB'
+            # 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)
             e = compat_urllib_parse_unquote(key)
             o = ''.join([
                 compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)


@@ -101,5 +133,5 @@ class BeegIE(InfoExtractor):
             'duration': duration,
             'tags': tags,
             'formats': formats,
             'duration': duration,
             'tags': tags,
             'formats': formats,

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

         }
         }