[eporner] Simplify and correct (#3629)

youtube_dl/extractor/eporner.py

@@ -4,10 +4,14 @@ 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<title_dash>[\w-]+)/?'
     _TEST = {
         'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
         'md5': '3b427ae4b9d60619106de3185c2987cd',
@@ -15,7 +19,8 @@ class EpornerIE(InfoExtractor):
             'id': '95008',
             'ext': 'flv',
             'title': 'Infamous Tiffany Teen Strip Tease Video',
-            'duration': 194
+            'duration': 194,
+            'view_count': int,
         }
     }
 
@@ -23,27 +28,28 @@ class EpornerIE(InfoExtractor):
         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')
+        title = self._html_search_regex(
+            r'<title>(.*?) - EPORNER', webpage, 'title')
 
-        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
+        redirect_code = self._html_search_regex(
+            r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
+            webpage, 'redirect_code')
+        redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
         webpage2 = self._download_webpage(redirect_url, video_id)
-        video_url = self._html_search_regex(r'file: "(.*?)",', webpage2, 'video_url')
-
-        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
+        video_url = self._html_search_regex(
+            r'file: "(.*?)",', webpage2, 'video_url')
 
-        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._search_regex(
+            r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
+            fatal=False))
+        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,
             'title': title,
-            'duration': int_or_none(duration),
-            'view_count': int_or_none(view_count),
+            'duration': duration,
+            'view_count': view_count,
         }

youtube_dl/utils.py

@@ -1318,6 +1318,7 @@ def str_or_none(v, default=None):
 
 
 def str_to_int(int_str):
+    """ A more relaxed version of int_or_none """
     if int_str is None:
         return None
     int_str = re.sub(r'[,\.]', u'', int_str)