[nuevo] Simplify nuevo extractors (Closes #7728)

youtube_dl/extractor/anitube.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .nuevo import NuevoBaseIE
 
 
@@ -22,12 +20,11 @@ class AnitubeIE(NuevoBaseIE):
     }
 
     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)
         key = self._search_regex(
             r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
 
-        config_url = 'http://www.anitube.se/nuevo/econfig.php?key=%s' % key
-        return self._extract_nuevo(config_url, video_id)
+        return self._extract_nuevo(
+            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, video_id)

youtube_dl/extractor/nuevo.py

@@ -11,22 +11,23 @@ from ..utils import (
 
 class NuevoBaseIE(InfoExtractor):
     def _extract_nuevo(self, config_url, video_id):
-        tree = self._download_xml(config_url, video_id, transform_source=lambda s: s.strip())
+        config = self._download_xml(
+            config_url, video_id, transform_source=lambda s: s.strip())
 
-        title = xpath_text(tree, './title')
-        if title:
-            title = title.strip()
-
-        thumbnail = xpath_text(tree, './image')
-        duration = float_or_none(xpath_text(tree, './duration'))
+        title = xpath_text(config, './title', 'title', fatal=True).strip()
+        video_id = xpath_text(config, './mediaid', default=video_id)
+        thumbnail = xpath_text(config, './image')
+        duration = float_or_none(xpath_text(config, './duration'))
 
         formats = []
         for element_name, format_id in (('file', 'sd'), ('filehd', 'hd')):
-            video_url = tree.find(element_name)
-            video_url is None or formats.append({
-                'format_id': format_id,
-                'url': video_url.text
-            })
+            video_url = xpath_text(config, element_name)
+            if video_url:
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                })
+        self._check_formats(formats, video_id)
 
         return {
             'id': video_id,

youtube_dl/extractor/trollvids.py

@@ -1,49 +1,36 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-from .nuevo import NuevoBaseIE
-
-from ..compat import (
-    compat_urllib_parse_unquote
-)
-
 import re
 
+from .nuevo import NuevoBaseIE
+
 
 class TrollvidsIE(NuevoBaseIE):
-    _VALID_URL = r'http://(?:www\.)?trollvids\.com/+video/+(?P<id>[0-9]+)/+(?P<title>[^?&]+)'
+    _VALID_URL = r'http://(?:www\.)?trollvids\.com/video/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
     IE_NAME = 'trollvids'
+    _TEST = {
+        'url': 'http://trollvids.com/video/2349002/%E3%80%90MMD-R-18%E3%80%91%E3%82%AC%E3%83%BC%E3%83%AB%E3%83%95%E3%83%AC%E3%83%B3%E3%83%89-carrymeoff',
+        'md5': '1d53866b2c514b23ed69e4352fdc9839',
+        'info_dict': {
+            'id': '2349002',
+            'ext': 'mp4',
+            'title': '【MMD R-18】ガールフレンド carry_me_off',
+            'age_limit': 18,
+            'duration': 216.78,
+        },
+    }
 
     def _real_extract(self, url):
-        match = re.match(self._VALID_URL, url)
-
-        video_id = match.group('id')
-        raw_video_title = match.group('title')
-        url = 'http://trollvids.com/video/%s/%s' % (video_id, raw_video_title)
-        config_url = 'http://trollvids.com/nuevo/player/config.php?v=%s' % video_id
-
-        info = self._extract_nuevo(config_url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
+        info = self._extract_nuevo(
+            'http://trollvids.com/nuevo/player/config.php?v=%s' % video_id,
+            video_id)
         info.update({
-            'webpage_url': url,
+            'display_id': display_id,
             'age_limit': 18
         })
-
-        if 'title' not in info:
-            info['title'] = compat_urllib_parse_unquote(raw_video_title)
-
         return info
-
-    _TESTS = [
-        {
-            'url': 'http://trollvids.com/video/2349002/%E3%80%90MMD-R-18%E3%80%91%E3%82%AC%E3%83%BC%E3%83%AB%E3%83%95%E3%83%AC%E3%83%B3%E3%83%89-carrymeoff',
-            'md5': '1d53866b2c514b23ed69e4352fdc9839',
-            'info_dict': {
-                'id': '2349002',
-                'ext': 'mp4',
-                'title': "【MMD R-18】ガールフレンド carry_me_off",
-                'age_limit': 18,
-                'duration': 216.78,
-            },
-        },
-    ]

youtube_dl/extractor/trutube.py

@@ -4,7 +4,7 @@ from .nuevo import NuevoBaseIE
 
 
 class TruTubeIE(NuevoBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?trutube\.tv/(?:video/|nuevo/player/embed\.php\?v=)(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?trutube\.tv/(?:video/|nuevo/player/embed\.php\?v=)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-',
         'md5': 'c5b6e301b0a2040b074746cbeaa26ca1',
@@ -21,11 +21,6 @@ class TruTubeIE(NuevoBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        config_url = 'https://trutube.tv/nuevo/player/config.php?v=%s' % video_id
-
-        info = self._extract_nuevo(config_url, video_id)
-
-        # filehd always 404s
-        info['formats'] = info['formats'][:1]
-
-        return info
+        return self._extract_nuevo(
+            'https://trutube.tv/nuevo/player/config.php?v=%s' % video_id,
+            video_id)