debian/copyright: use spaces rather than tabs to start continuation lines.

[youtubedl] / youtube_dl / extractor / beeg.py

diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
index 956c7680e2ecc46a1df493947ed0be7b973d81b8..5788d13baae816ad69155d42f5f2d2b5ce837231 100644 (file)
--- a/youtube_dl/extractor/beeg.py
+++ b/youtube_dl/extractor/beeg.py
@@ -2,21 +2,21 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_chr,
-    compat_ord,
-    compat_urllib_parse_unquote,
+    compat_str,
+    compat_urlparse,
 )
 from ..utils import (
     int_or_none,
-    parse_iso8601,
+    unified_timestamp,
 )
 
 
 class BeegIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
+    _TESTS = [{
+        # api/v6 v1
         'url': 'http://beeg.com/5416503',
-        'md5': '46c384def73b33dbc581262e5ee67cef',
+        'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',
@@ -28,69 +28,52 @@ class BeegIE(InfoExtractor):
             'tags': list,
             'age_limit': 18,
         }
-    }
+    }, {
+        # api/v6 v2
+        'url': 'https://beeg.com/1941093077?t=911-1391',
+        'only_matching': True,
+    }, {
+        # api/v6 v2 w/o t
+        'url': 'https://beeg.com/1277207756',
+        'only_matching': True,
+    }, {
+        'url': 'https://beeg.porn/video/5416503',
+        'only_matching': True,
+    }, {
+        'url': 'https://beeg.porn/5416503',
+        'only_matching': True,
+    }]
 
     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 = self._search_regex(
-                    r'beeg_version\s*=\s*(\d+)', 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 beeg_salt',
-                    default=None, group='beeg_salt')
-
-        beeg_version = beeg_version or '1750'
-        beeg_salt = beeg_salt or 'MIDtGaw96f0N1kMMAM1DE46EC9pmFr'
-
-        video = self._download_json(
-            'http://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))
+        beeg_version = self._search_regex(
+            r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
+            default='1546225636701')
+
+        if len(video_id) >= 10:
+            query = {
+                'v': 2,
+            }
+            qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+            t = qs.get('t', [''])[0].split('-')
+            if len(t) > 1:
+                query.update({
+                    's': t[0],
+                    'e': t[1],
+                })
+        else:
+            query = {'v': 1}
+
+        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.', query=query)
+            if video:
+                break
 
         formats = []
         for format_id, video_url in video.items():
@@ -101,18 +84,20 @@ class BeegIE(InfoExtractor):
             if not height:
                 continue
             formats.append({
-                'url': decrypt_url(video_url),
+                'url': self._proto_relative_url(
+                    video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
                 'format_id': format_id,
                 'height': int(height),
             })
         self._sort_formats(formats)
 
         title = video['title']
-        video_id = video.get('id') or video_id
+        video_id = compat_str(video.get('id') or video_id)
         display_id = video.get('code')
         description = video.get('desc')
+        series = video.get('ps_name')
 
-        timestamp = parse_iso8601(video.get('date'), ' ')
+        timestamp = unified_timestamp(video.get('date'))
         duration = int_or_none(video.get('duration'))
 
         tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
@@ -122,6 +107,7 @@ class BeegIE(InfoExtractor):
             'display_id': display_id,
             'title': title,
             'description': description,
+            'series': series,
             'timestamp': timestamp,
             'duration': duration,
             'tags': tags,