[presstv] Improve and simplify
authorYen Chi Hsuan <yan12125@gmail.com>
Mon, 11 Apr 2016 08:14:07 +0000 (16:14 +0800)
committerYen Chi Hsuan <yan12125@gmail.com>
Mon, 11 Apr 2016 08:14:07 +0000 (16:14 +0800)
youtube_dl/extractor/presstv.py

index 755e3252857cd15cb63b5405506ff9a83c06d860..2da93ed348671a363120d03cb626a4e9d808fd9d 100644 (file)
@@ -1,19 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import str_to_int
+from ..utils import remove_start
 
 
 class PressTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>[0-9]+)/(?P<m>[0-9]+)/(?P<d>[0-9]+)/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>\d+)/(?P<m>\d+)/(?P<d>\d+)/(?P<id>\d+)/(?P<display_id>[^/]+)?'
 
     _TEST = {
         'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/',
         'md5': '5d7e3195a447cb13e9267e931d8dd5a5',
         'info_dict': {
             'id': '459911',
+            'display_id': 'Australian-sewerage-treatment-facility-',
             'ext': 'mp4',
             'title': 'Organic mattresses used to clean waste water',
             'upload_date': '20160409',
@@ -23,47 +25,47 @@ class PressTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(url, display_id)
 
         # extract video URL from webpage
-        video_url = self._html_search_regex(r'<input type="hidden" id="inpPlayback" value="([^"]+)" />', webpage,
-                                            'Video URL')
+        video_url = self._hidden_inputs(webpage)['inpPlayback']
 
         # build list of available formats
         # specified in http://www.presstv.ir/Scripts/playback.js
         base_url = 'http://192.99.219.222:82/presstv'
         _formats = [
-            ("180p", "_low200.mp4"),
-            ("360p", "_low400.mp4"),
-            ("720p", "_low800.mp4"),
-            ("1080p", ".mp4")
+            (180, '_low200.mp4'),
+            (360, '_low400.mp4'),
+            (720, '_low800.mp4'),
+            (1080, '.mp4')
         ]
 
-        formats = []
-        for fmt in _formats:
-            format_id, extension = fmt
-            formats.append({
-                'url': base_url + video_url[:-4] + extension,
-                'format_id': format_id
-            })
+        formats = [{
+            'url': base_url + video_url[:-4] + extension,
+            'format_id': '%dp' % height,
+            'height': height,
+        } for height, extension in _formats]
 
         # extract video metadata
-        title = self._html_search_meta('title', webpage, 'Title', True)
-        title = title.partition('-')[2].strip()
+        title = remove_start(
+            self._html_search_meta('title', webpage, fatal=True), 'PressTV-')
 
         thumbnail = self._og_search_thumbnail(webpage)
         description = self._og_search_description(webpage)
 
-        match = re.match(PressTVIE._VALID_URL, url)
         upload_date = '%04d%02d%02d' % (
-            str_to_int(match.group('y')),
-            str_to_int(match.group('m')),
-            str_to_int(match.group('d'))
+            int(mobj.group('y')),
+            int(mobj.group('m')),
+            int(mobj.group('d')),
         )
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': title,
             'formats': formats,
             'thumbnail': thumbnail,