Merge branch 'peugeot-tnaflix'

youtube_dl/extractor/__init__.py

@@ -86,7 +86,7 @@ from .ellentv import (
     EllenTVClipsIE,
 )
 from .elpais import ElPaisIE
-from .empflix import EmpflixIE
+from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .escapist import EscapistIE
@@ -348,6 +348,7 @@ from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
+from .tnaflix import TNAFlixIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE

youtube_dl/extractor/empflix.py

@@ -1,58 +1,25 @@
 from __future__ import unicode_literals
 
-import re
+from .tnaflix import TNAFlixIE
 
-from .common import InfoExtractor
-from ..utils import fix_xml_ampersands
 
+class EMPFlixIE(TNAFlixIE):
+    _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html'
+
+    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
+    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
+    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
 
-class EmpflixIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
     _TEST = {
         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
         'info_dict': {
             'id': '33051',
+            'display_id': 'Amateur-Finger-Fuck',
             'ext': 'mp4',
             'title': 'Amateur Finger Fuck',
             'description': 'Amateur solo finger fucking.',
+            'thumbnail': 're:https?://.*\.jpg$',
             '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)
-        age_limit = self._rta_search(webpage)
-
-        video_title = self._html_search_regex(
-            r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
-        video_description = self._html_search_regex(
-            r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
-
-        cfg_url = self._html_search_regex(
-            r'flashvars\.config = escape\("([^"]+)"',
-            webpage, 'flashvars.config')
-
-        cfg_xml = self._download_xml(
-            cfg_url, video_id, note='Downloading metadata',
-            transform_source=fix_xml_ampersands)
-
-        formats = [
-            {
-                'url': item.find('videoLink').text,
-                'format_id': item.find('res').text,
-            } for item in cfg_xml.findall('./quality/item')
-        ]
-        thumbnail = cfg_xml.find('./startThumb').text
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'description': video_description,
-            'thumbnail': thumbnail,
-            'formats': formats,
-            'age_limit': age_limit,
-        }

youtube_dl/extractor/tnaflix.py

@@ -0,0 +1,84 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    fix_xml_ampersands,
+)
+
+
+class TNAFlixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)'
+
+    _TITLE_REGEX = None
+    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
+
+    _TEST = {
+        'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+        'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+        'info_dict': {
+            'id': '553878',
+            'display_id': 'Carmella-Decesare-striptease',
+            'ext': 'mp4',
+            'title': 'Carmella Decesare - striptease',
+            'description': '',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 91,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_regex(
+            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
+        description = self._html_search_regex(
+            self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
+
+        age_limit = self._rta_search(webpage)
+
+        duration = self._html_search_meta('duration', webpage, 'duration', default=None)
+        if duration:
+            duration = parse_duration(duration[1:])
+
+        cfg_url = self._html_search_regex(
+            self._CONFIG_REGEX, webpage, 'flashvars.config')
+
+        cfg_xml = self._download_xml(
+            cfg_url, display_id, note='Downloading metadata',
+            transform_source=fix_xml_ampersands)
+
+        thumbnail = cfg_xml.find('./startThumb').text
+
+        formats = []
+        for item in cfg_xml.findall('./quality/item'):
+            video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
+            format_id = item.find('res').text
+            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)
+        
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/utils.py

@@ -1336,7 +1336,7 @@ def parse_duration(s):
     s = s.strip()
 
     m = re.match(
-        r'(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s)
+        r'(?i)(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s)
     if not m:
         return None
     res = int(m.group('secs'))