w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[clipfish] extract mp4 video link

Browse source
This commit is contained in:
remitamine 2015-07-24 12:00:20 +01:00
parent 53b8247cb5
commit 1a117a7728
1 changed files with 19 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
youtube_dl/extractor/clipfish.py
View file

@ -1,13 +1,11 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
import time
import xml.etree.ElementTree
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
parse_duration, int_or_none,
js_to_json,
determine_ext,
) )
@ -17,37 +15,40 @@ class ClipfishIE(InfoExtractor):
_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 = { _TEST = {
'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/', 'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
'md5': '2521cd644e862936cf2e698206e47385', 'md5': '79bc922f3e8a9097b3d68a93780fd475',
'info_dict': { 'info_dict': {
'id': '3966754', 'id': '3966754',
'ext': 'mp4', 'ext': 'mp4',
'title': 'FIFA 14 - E3 2013 Trailer', 'title': 'FIFA 14 - E3 2013 Trailer',
'duration': 82, 'duration': 82,
}, }
'skip': 'Blocked in the US'
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group(1) webpage = self._download_webpage(url, video_id)
video_info = self._parse_json(
js_to_json(self._html_search_regex('var videoObject = ({[^}]+?})', webpage, 'videoObject')),
video_id
)
info_url = self._parse_json(
js_to_json(self._html_search_regex('var globalFlashvars = ({[^}]+?})', webpage, 'globalFlashvars')),
video_id
)['data']
info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
(video_id, int(time.time())))
doc = self._download_xml( doc = self._download_xml(
info_url, video_id, note='Downloading info page') info_url, video_id, note='Downloading info page')
title = doc.find('title').text title = doc.find('title').text
video_url = doc.find('filename').text video_url = doc.find('filename').text
if video_url is None:
xml_bytes = xml.etree.ElementTree.tostring(doc)
raise ExtractorError('Cannot find video URL in document %r' %
xml_bytes)
thumbnail = doc.find('imageurl').text thumbnail = doc.find('imageurl').text
duration = parse_duration(doc.find('duration').text) duration = int_or_none(video_info['length'])
formats = [{'url': video_info['videourl']},{'url': video_url}]
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'formats': formats,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
} }