diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/brightcove.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/firstpost.py | 29 | ||||
| -rw-r--r-- | youtube_dl/extractor/prosiebensat1.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/weibo.py | 30 |
4 files changed, 40 insertions, 26 deletions
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 339d60ff0..3c02c297a 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -140,7 +140,11 @@ class BrightcoveIE(InfoExtractor): url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage) if url_m: - return [unescapeHTML(url_m.group(1))] + url = unescapeHTML(url_m.group(1)) + # Some sites don't add it, we can't download with this url, for example: + # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/ + if 'playerKey' in url: + return [url] matches = re.findall( r'''(?sx)<object diff --git a/youtube_dl/extractor/firstpost.py b/youtube_dl/extractor/firstpost.py index 7e3d1afd2..eccd8dde9 100644 --- a/youtube_dl/extractor/firstpost.py +++ b/youtube_dl/extractor/firstpost.py @@ -6,7 +6,6 @@ from .common import InfoExtractor class FirstpostIE(InfoExtractor): - IE_NAME = 'Firstpost.com' _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html' _TEST = { @@ -16,7 +15,6 @@ class FirstpostIE(InfoExtractor): 'id': '1025403', 'ext': 'mp4', 'title': 'India to launch indigenous aircraft carrier INS Vikrant today', - 'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.', } } @@ -24,15 +22,26 @@ class FirstpostIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'<div.*?name="div_video".*?flashvars="([^"]+)">', - webpage, 'video URL') + data = self._download_xml( + 'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id, + 'Downloading video XML') + + item = data.find('./playlist/item') + thumbnail = item.find('./image').text + title = item.find('./title').text + + formats = [ + { + 'url': details.find('./file').text, + 'format_id': details.find('./label').text.strip(), + 'width': int(details.find('./width').text.strip()), + 'height': int(details.find('./height').text.strip()), + } for details in item.findall('./source/file_details') if details.find('./file').text + ] return { 'id': video_id, - 'url': video_url, - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, } diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 3f585bebf..1e84b175f 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -160,6 +160,7 @@ class ProSiebenSat1IE(InfoExtractor): _CLIPID_REGEXES = [ r'"clip_id"\s*:\s+"(\d+)"', r'clipid: "(\d+)"', + r'clipId=(\d+)', ] _TITLE_REGEXES = [ r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>', diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py index fa784ab99..b24297a40 100644 --- a/youtube_dl/extractor/weibo.py +++ b/youtube_dl/extractor/weibo.py @@ -1,10 +1,11 @@ # coding: utf-8 +from __future__ import unicode_literals import re -import json from .common import InfoExtractor + class WeiboIE(InfoExtractor): """ The videos in Weibo come from different sites, this IE just finds the link @@ -13,16 +14,16 @@ class WeiboIE(InfoExtractor): _VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm' _TEST = { - u'add_ie': ['Sina'], - u'url': u'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm', - u'file': u'98322879.flv', - u'info_dict': { - u'title': u'魔声耳机最新广告“All Eyes On Us”', + 'url': 'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm', + 'info_dict': { + 'id': '98322879', + 'ext': 'flv', + 'title': '魔声耳机最新广告“All Eyes On Us”', }, - u'note': u'Sina video', - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, + 'add_ie': ['Sina'], } # Additional example videos from different sites @@ -33,17 +34,16 @@ class WeiboIE(InfoExtractor): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) video_id = mobj.group('id') info_url = 'http://video.weibo.com/?s=v&a=play_list&format=json&mix_video_id=t_%s' % video_id - info_page = self._download_webpage(info_url, video_id) - info = json.loads(info_page) + info = self._download_json(info_url, video_id) videos_urls = map(lambda v: v['play_page_url'], info['result']['data']) - #Prefer sina video since they have thumbnails - videos_urls = sorted(videos_urls, key=lambda u: u'video.sina.com' in u) + # Prefer sina video since they have thumbnails + videos_urls = sorted(videos_urls, key=lambda u: 'video.sina.com' in u) player_url = videos_urls[-1] - m_sina = re.match(r'https?://video.sina.com.cn/v/b/(\d+)-\d+.html', player_url) + m_sina = re.match(r'https?://video\.sina\.com\.cn/v/b/(\d+)-\d+\.html', + player_url) if m_sina is not None: self.to_screen('Sina video detected') sina_id = m_sina.group(1) player_url = 'http://you.video.sina.com.cn/swf/quotePlayer.swf?vid=%s' % sina_id return self.url_result(player_url) - |