Merge remote-tracking branch 'duncankl/airmozilla'
[youtube-dl] / youtube_dl / extractor / eporner.py
index 72c3850b7331dee07b6ae16b121303b61ae21264..e006921ec3f8d2a0aff0e6bb0595148469b1c256 100644 (file)
@@ -4,46 +4,67 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    parse_duration,
+    str_to_int,
+)
+
 
 class EpornerIE(InfoExtractor):
-    _VALID_URL = r'http?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<title_dash>[\w-]+)/?'
+    _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)'
     _TEST = {
         'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
-        'md5': '3b427ae4b9d60619106de3185c2987cd',
+        'md5': '39d486f046212d8e1b911c52ab4691f8',
         'info_dict': {
             'id': '95008',
-            'ext': 'flv',
+            'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
+            'ext': 'mp4',
             'title': 'Infamous Tiffany Teen Strip Tease Video',
-            'duration': 194
+            'duration': 1838,
+            'view_count': int,
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<title>(.*?) - EPORNER', webpage, 'title')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+        title = self._html_search_regex(
+            r'<title>(.*?) - EPORNER', webpage, 'title')
+
+        redirect_url = 'http://www.eporner.com/config5/%s' % video_id
+        player_code = self._download_webpage(
+            redirect_url, display_id, note='Downloading player config')
 
-        redirect_code = self._html_search_regex(r'<script type="text/javascript" src="/config5/'+str(video_id)+'/([a-f\d]+)/">', webpage, 'redirect_code')
-        redirect_url = 'http://www.eporner.com/config5/' + str(video_id) +'/'+ redirect_code
-        webpage2 = self._download_webpage(redirect_url, video_id)
-        video_url = self._html_search_regex(r'file: "(.*?)",', webpage2, 'video_url')
+        sources = self._search_regex(
+            r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
 
-        mobj = re.search(r'class="mbtim">(?P<minutes>\d+):(?P<seconds>\d+)</div>', webpage)
-        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+        formats = []
+        for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
+            fmt = {
+                'url': video_url,
+                'format_id': format_id,
+            }
+            m = re.search(r'^(\d+)', format_id)
+            if m:
+                fmt['height'] = int(m.group(1))
+            formats.append(fmt)
+        self._sort_formats(formats)
 
-        mobj = re.search(r'id="cinemaviews">((?P<thousands>\d+),)?(?P<units>\d+)<small>views', webpage)
-        try:
-            view_count = int(mobj.group('units'))
-            view_count += int(mobj.group('thousands')) * 1000
-        except:
-            pass
+        duration = parse_duration(self._html_search_meta('duration', webpage))
+        view_count = str_to_int(self._search_regex(
+            r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
+            webpage, 'view count', fatal=False))
 
         return {
             'id': video_id,
-            'url': video_url,
+            'display_id': display_id,
             'title': title,
-            'duration': int_or_none(duration),
-            'view_count': int_or_none(view_count),
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': 18,
         }