Merge pull request #4 from debian-janitor/lintian-fixes

[youtubedl] / youtube_dl / extractor / beeg.py

diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
index b38057f2f500f520829ff9c5d7324e66558eb356..5788d13baae816ad69155d42f5f2d2b5ce837231 100644 (file)
--- a/youtube_dl/extractor/beeg.py
+++ b/youtube_dl/extractor/beeg.py
@@ -1,65 +1,116 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    int_or_none,
+    unified_timestamp,
+)

 
 
 class BeegIE(InfoExtractor):
 
 
 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',
         'url': 'http://beeg.com/5416503',

-        'md5': '1bff67111adb785c51d1b42959ec10e5',
+        'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',

         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',
             'title': 'Sultry Striptease',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',
             'title': 'Sultry Striptease',

-            'description': 'md5:6db3c6177972822aaba18652ff59c773',
-            'categories': list,  # NSFW
-            'thumbnail': 're:https?://.*\.jpg$',
+            'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
+            'timestamp': 1391813355,
+            'upload_date': '20140207',
+            'duration': 383,
+            'tags': list,

             'age_limit': 18,
         }
             '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):
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

 
         webpage = self._download_webpage(url, video_id)
 
 
         webpage = self._download_webpage(url, video_id)
 

-        quality_arr = self._search_regex(
-            r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
+        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}

 
 

-        formats = [{
-            'url': fmt[1],
-            'format_id': fmt[0],
-            'height': int(fmt[0][:-1]),
-        } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
+        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():
+            if not video_url:
+                continue
+            height = self._search_regex(
+                r'^(\d+)[pP]$', format_id, 'height', default=None)
+            if not height:
+                continue
+            formats.append({
+                '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)
 
         self._sort_formats(formats)
 

-        title = self._html_search_regex(
-            r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
+        title = video['title']
+        video_id = compat_str(video.get('id') or video_id)
+        display_id = video.get('code')
+        description = video.get('desc')
+        series = video.get('ps_name')

 
 

-        description = self._html_search_regex(
-            r'<meta name="description" content="([^"]*)"',
-            webpage, 'description', fatal=False)
-        thumbnail = self._html_search_regex(
-            r'\'previewer.url\'\s*:\s*"([^"]*)"',
-            webpage, 'thumbnail', fatal=False)
+        timestamp = unified_timestamp(video.get('date'))
+        duration = int_or_none(video.get('duration'))

 
 

-        categories_str = self._html_search_regex(
-            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
-        categories = (
-            None if categories_str is None
-            else categories_str.split(','))
+        tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

+            'display_id': display_id,

             'title': title,
             'description': description,
             'title': title,
             'description': description,

-            'thumbnail': thumbnail,
-            'categories': categories,
+            'series': series,
+            'timestamp': timestamp,
+            'duration': duration,
+            'tags': tags,

             'formats': formats,
             'formats': formats,

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

         }
         }