youtube-dl

commit 5a8b77551d930d4672159a015f553e64be111492
parent 0217aee154e9f0f5f0c82c3253046c925d4073eb
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sun, 28 Sep 2014 10:40:49 +0200

[heise] Simplify (#3842)

Diffstat:
M
youtube_dl/extractor/heise.py
 | 
92
+++++++++++++++++++++++--------------------------------------------------------

1 file changed, 26 insertions(+), 66 deletions(-)
diff --git a/youtube_dl/extractor/heise.py b/youtube_dl/extractor/heise.py
@@ -1,34 +1,28 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
-    compat_urllib_parse,
     get_meta_content,
     parse_iso8601,
 )
 
 
 class HeiseIE(InfoExtractor):
-    _VALID_URL = (
-        r'^https?://(?:www\.)?heise\.de/video/artikel/' +
-        r'.+?(?P<id>[0-9]+)\.html$'
-    )
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?heise\.de/video/artikel/
+        .+?(?P<id>[0-9]+)\.html(?:$|[?#])
+    '''
     _TEST = {
         'url': (
-            'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-' +
-            'Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
+            'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
         ),
         'md5': 'ffed432483e922e88545ad9f2f15d30e',
         'info_dict': {
             'id': '2404147',
             'ext': 'mp4',
             'title': (
-                "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / " +
-                "Peilsender Smartphone"
+                "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
             ),
             'format_id': 'mp4_720',
             'timestamp': 1411812600,
@@ -36,84 +30,50 @@ class HeiseIE(InfoExtractor):
         }
     }
 
-    _CONFIG = (
-        r'".+?\?sequenz=(?P<sequenz>.+?)&container=(?P<container>.+?)' +
-        r'(?:&hd=(?P<hd>.+?))?(?:&signature=(?P<signature>.+?))?&callback=\?"'
-    )
-    _PREFIX = 'http://www.heise.de/videout/info?'
-
-    def _warn(self, fmt, *args):
-        self.report_warning(fmt.format(*args), self._id)
-
-    def _parse_config_url(self, html):
-        m = re.search(self._CONFIG, html)
-        if not m:
-            raise ExtractorError('No config found')
-
-        qs = compat_urllib_parse.urlencode(dict((k, v) for k, v
-                                                in m.groupdict().items()
-                                                if v is not None))
-        return self._PREFIX + qs
-
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        self._id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        html = self._download_webpage(url, self._id)
-        config = self._download_json(self._parse_config_url(html), self._id)
+        webpage = self._download_webpage(url, video_id)
+        json_url = self._search_regex(
+            r'json_url:\s*"([^"]+)"', webpage, 'json URL')
+        config = self._download_json(json_url, video_id)
 
         info = {
-            'id': self._id
+            'id': video_id,
+            'thumbnail': config.get('poster'),
+            'timestamp': parse_iso8601(get_meta_content('date', webpage)),
         }
 
-        title = get_meta_content('fulltitle', html)
+        title = get_meta_content('fulltitle', webpage)
         if title:
             info['title'] = title
         elif config.get('title'):
             info['title'] = config['title']
         else:
-            self._warn('title: not found')
-            info['title'] = 'heise'
-
-        if (not config.get('formats') or
-                not hasattr(config['formats'], 'items')):
-            raise ExtractorError('No formats found')
+            info['title'] = self._og_search_title(webpage)
 
         formats = []
         for t, rs in config['formats'].items():
             if not rs or not hasattr(rs, 'items'):
-                self._warn('formats: {0}: no resolutions', t)
+                self._downloader.report_warning(
+                    'formats: {0}: no resolutions'.format(t))
                 continue
 
-            for res, obj in rs.items():
-                format_id = '{0}_{1}'.format(t, res)
+            for height_str, obj in rs.items():
+                format_id = '{0}_{1}'.format(t, height_str)
 
                 if not obj or not obj.get('url'):
-                    self._warn('formats: {0}: no url', format_id)
+                    self._downloader.report_warning(
+                        'formats: {0}: no url'.format(format_id))
                     continue
 
-                fmt = {
+                formats.append({
                     'url': obj['url'],
-                    'format_id': format_id
-                }
-                try:
-                    fmt['height'] = int(res)
-                except ValueError as e:
-                    self._warn('formats: {0}: height: {1}', t, e)
-
-                formats.append(fmt)
+                    'format_id': format_id,
+                    'height': self._int(height_str, 'height'),
+                })
 
         self._sort_formats(formats)
         info['formats'] = formats
 
-        if config.get('poster'):
-            info['thumbnail'] = config['poster']
-
-        date = get_meta_content('date', html)
-        if date:
-            try:
-                info['timestamp'] = parse_iso8601(date)
-            except ValueError as e:
-                self._warn('timestamp: {0}', e)
-
         return info