[pornovoisines] Simplify

youtube_dl/extractor/pornovoisines.py

@@ -2,19 +2,23 @@
 from __future__ import unicode_literals
 
 import re
-import datetime
 import random
 
-from ..compat import compat_urllib_parse
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    unified_strdate,
+)
+
 
 class PornoVoisinesIE(InfoExtractor):
-    _VALID_URL = r'^((?:http://)?(?:www\.)?pornovoisines.com)/showvideo/(\d+)/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
 
-    VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
+    _VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
         '/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
 
-    SERVER_NUMBERS = (1, 2)
+    _SERVER_NUMBERS = (1, 2)
 
     _TEST = {
         'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
@@ -23,79 +27,70 @@ class PornoVoisinesIE(InfoExtractor):
             'id': '1285',
             'display_id': 'recherche-appartement',
             'ext': 'mp4',
-            'title': "Recherche appartement",
+            'title': 'Recherche appartement',
+            'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
+            'thumbnail': 're:^https?://.*\.jpg$',
             'upload_date': '20140925',
-            'view_count': int,
             'duration': 120,
-            'categories': ["Débutante", "Scénario", "Sodomie"],
+            'view_count': int,
-            'description': 're:^Pour la .+ original...$',
-            'thumbnail': 're:^http://',
-            'uploader': "JMTV",
             'average_rating': float,
-            'comment_count': int,
+            'categories': ['Débutante', 'Scénario', 'Sodomie'],
             'age_limit': 18,
         }
     }
 
     @classmethod
-    def build_video_url(cls, id):
+    def build_video_url(cls, num):
-        server_nr = random.choice(cls.SERVER_NUMBERS)
+        return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num)
-        return cls.VIDEO_URL_TEMPLATE % (server_nr, id)
-
-    @staticmethod
-    def parse_upload_date(str):
-        return datetime.datetime.strptime(str, "%d-%m-%Y").strftime("%Y%m%d")
-
-    @staticmethod
-    def parse_categories(str):
-        return map(lambda s: s.strip(), str.split(','))
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        url_prefix = mobj.group(1)
+        video_id = mobj.group('id')
-        id = mobj.group(2)
+        display_id = mobj.group('display_id')
-        display_id = mobj.group(3)
 
-        webpage = self._download_webpage(url, id)
+        webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title',
+        video_url = self.build_video_url(video_id)
-            flags=re.DOTALL)
+
-        url = self.build_video_url(id)
+        title = self._html_search_regex(
-        upload_date = self.parse_upload_date(
+            r'<h1>(.+?)</h1>', webpage, 'title', flags=re.DOTALL)
-            self._search_regex(r'Publié le (\d\d-\d\d-\d{4})', webpage,
-            'upload date'))
-        view_count = int(self._search_regex(r'(\d+) vues', webpage, 'view count'))
-        duration = int(self._search_regex('Durée (\d+)', webpage, 'duration'))
-        categories = self.parse_categories(self._html_search_regex(
-            r'<li class="categorie">(.+?)</li>', webpage, "categories",
-            flags=re.DOTALL))
         description = self._html_search_regex(
-            r'<article id="descriptif">(.+?)</article>', webpage, "description",
+            r'<article id="descriptif">(.+?)</article>',
-            flags=re.DOTALL)
+            webpage, "description", fatal=False, flags=re.DOTALL)
-        thumbnail = url_prefix + self._html_search_regex(re.compile(
+
-            '<div id="mediaspace' + id + '">.*?<img src="(.+?)"', re.DOTALL),
+        thumbnail = self._search_regex(
-            webpage, "thumbnail")
+            r'<div id="mediaspace%s">\s*<img src="/?([^"]+)"' % video_id,
-        uploader = re.sub(r' *\| *$', '',
+            webpage, 'thumbnail', fatal=False)
-            self._html_search_regex(r'<li class="auteur">(.+?)</li>', webpage,
+        if thumbnail:
-            "uploader", flags=re.DOTALL))
+            thumbnail = 'http://www.pornovoisines.com/%s' % thumbnail
-        average_rating = float(self._search_regex(r'Note : (\d+,\d+)',
+
-            webpage, "average rating").replace(',', '.'))
+        upload_date = unified_strdate(self._search_regex(
-        comment_count = int(self._search_regex(r'\((\d+)\)', webpage,
+            r'Publié le ([\d-]+)', webpage, 'upload date', fatal=False))
-            "comment count"))
+        duration = int_or_none(self._search_regex(
+            'Durée (\d+)', webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'(\d+) vues', webpage, 'view count', fatal=False))
+        average_rating = self._search_regex(
+            r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False)
+        if average_rating:
+            average_rating = float_or_none(average_rating.replace(',', '.'))
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', fatal=False)
+        if categories:
+            categories = [category.strip() for category in categories.split(',')]
 
         return {
-            'id': id,
+            'id': video_id,
             'display_id': display_id,
-            'url': url,
+            'url': video_url,
             'title': title,
-            'upload_date': upload_date,
-            'view_count': view_count,
-            'duration': duration,
-            'categories': categories,
             'description': description,
             'thumbnail': thumbnail,
-            'uploader': uploader,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
             'average_rating': average_rating,
-            'comment_count': comment_count,
+            'categories': categories,
             'age_limit': 18,
         }