debian/README.source: Change 'markup'.

[youtubedl] / youtube_dl / extractor / kontrtube.py

diff --git a/youtube_dl/extractor/kontrtube.py b/youtube_dl/extractor/kontrtube.py
index 1b45b67b0579d9fb06462f587651bc8f83e4751d..1fda451075e4e0638e0799fc2bb976f21a4bcf8e 100644 (file)
--- a/youtube_dl/extractor/kontrtube.py
+++ b/youtube_dl/extractor/kontrtube.py
@@ -1,21 +1,26 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor

+from ..utils import (
+    int_or_none,
+    parse_duration,
+)

 
 
 class KontrTubeIE(InfoExtractor):
     IE_NAME = 'kontrtube'
     IE_DESC = 'KontrTube.ru - Труба зовёт'
 
 
 class KontrTubeIE(InfoExtractor):
     IE_NAME = 'kontrtube'
     IE_DESC = 'KontrTube.ru - Труба зовёт'

-    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
+    _VALID_URL = r'https?://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'

 
     _TEST = {
         'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
         'md5': '975a991a4926c9a85f383a736a2e6b80',
         'info_dict': {
             'id': '2678',
 
     _TEST = {
         'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
         'md5': '975a991a4926c9a85f383a736a2e6b80',
         'info_dict': {
             'id': '2678',

+            'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag',

             'ext': 'mp4',
             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
             'ext': 'mp4',
             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',


@@ -27,40 +32,42 @@ class KontrTubeIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

+        display_id = mobj.group('display_id')

 
 

-        webpage = self._download_webpage(url, video_id, 'Downloading page')
+        webpage = self._download_webpage(
+            url, display_id, 'Downloading page')

 
 

-        video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
-        thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
-        title = self._html_search_regex(r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage,
-            'video title')
-        description = self._html_search_meta('description', webpage, 'video description')
+        video_url = self._search_regex(
+            r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
+        thumbnail = self._search_regex(
+            r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False)
+        title = self._html_search_regex(
+            r'(?s)<h2>(.+?)</h2>', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description')

 
 

-        mobj = re.search(r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
-            webpage)
-        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+        duration = self._search_regex(
+            r'Длительность: <em>([^<]+)</em>', webpage, 'duration', fatal=False)
+        if duration:
+            duration = parse_duration(duration.replace('мин', 'min').replace('сек', 'sec'))

 
 

-        view_count = self._html_search_regex(r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage,
-            'view count', fatal=False)
-        view_count = int(view_count) if view_count is not None else None
+        view_count = self._search_regex(
+            r'Просмотров: <em>([^<]+)</em>',
+            webpage, 'view count', fatal=False)
+        if view_count:
+            view_count = int_or_none(view_count.replace(' ', ''))

 
 

-        comment_count = None
-        comment_str = self._html_search_regex(r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count',
-            fatal=False)
-        if comment_str.startswith('комментариев нет'):
-            comment_count = 0
-        else:
-            mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
-            if mobj:
-                comment_count = int(mobj.group('total'))
+        comment_count = int_or_none(self._search_regex(
+            r'Комментарии \((\d+)\)<', webpage, ' comment count', fatal=False))

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

+            'display_id': display_id,

             'url': video_url,
             'thumbnail': thumbnail,
             'title': title,
             'description': description,
             'duration': duration,
             'url': video_url,
             'thumbnail': thumbnail,
             'title': title,
             'description': description,
             'duration': duration,

-            'view_count': view_count,
-            'comment_count': comment_count,
-        }
\ No newline at end of file
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+        }