+from __future__ import unicode_literals
+
import re
-import time
-import xml.etree.ElementTree
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+ determine_ext,
+ int_or_none,
+ js_to_json,
+ parse_iso8601,
+ remove_end,
+)
class ClipfishIE(InfoExtractor):
- IE_NAME = u'clipfish'
-
- _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
+ _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
_TEST = {
- u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
- u'file': u'3966754.mp4',
- u'md5': u'2521cd644e862936cf2e698206e47385',
- u'info_dict': {
- u'title': u'FIFA 14 - E3 2013 Trailer',
- u'duration': 82,
- },
- u'skip': 'Blocked in the US'
+ 'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
+ 'md5': '79bc922f3e8a9097b3d68a93780fd475',
+ 'info_dict': {
+ 'id': '3966754',
+ 'ext': 'mp4',
+ 'title': 'FIFA 14 - E3 2013 Trailer',
+ 'timestamp': 1370938118,
+ 'upload_date': '20130611',
+ 'duration': 82,
+ }
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group(1)
-
- info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
- (video_id, int(time.time())))
- doc = self._download_xml(
- info_url, video_id, note=u'Downloading info page')
- title = doc.find('title').text
- video_url = doc.find('filename').text
- if video_url is None:
- xml_bytes = xml.etree.ElementTree.tostring(doc)
- raise ExtractorError(u'Cannot find video URL in document %r' %
- xml_bytes)
- thumbnail = doc.find('imageurl').text
- duration_str = doc.find('duration').text
- m = re.match(
- r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
- duration_str)
- if m:
- duration = (
- (int(m.group('hours')) * 60 * 60) +
- (int(m.group('minutes')) * 60) +
- (int(m.group('seconds')))
- )
- else:
- duration = None
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_info = self._parse_json(
+ js_to_json(self._html_search_regex(
+ '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
+ video_id)
+
+ formats = []
+ for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
+ ext = determine_ext(video_url)
+ if ext == 'm3u8':
+ formats.append({
+ 'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
+ 'ext': 'mp4',
+ 'format_id': 'hls',
+ })
+ else:
+ formats.append({
+ 'url': video_url,
+ 'format_id': ext,
+ })
+ self._sort_formats(formats)
+
+ title = remove_end(self._og_search_title(webpage), ' - Video')
+ thumbnail = self._og_search_thumbnail(webpage)
+ duration = int_or_none(video_info.get('length'))
+ timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
return {
'id': video_id,
'title': title,
- 'url': video_url,
+ 'formats': formats,
'thumbnail': thumbnail,
'duration': duration,
+ 'timestamp': timestamp,
}