Add arte.tv Info Extractor

This commit is contained in:
Christian Albrecht 2012-08-26 09:11:19 +02:00 committed by Christian Albrecht
parent 9bb8dc8e42
commit f2ad10a97d
2 changed files with 156 additions and 0 deletions

View file

@ -1077,6 +1077,161 @@ def _real_extract(self, url, new_video=True):
}] }]
class ArteTvIE(InfoExtractor):
"""arte.tv information extractor."""
_VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
_LIVE_URL = r'index-[0-9]+\.html$'
IE_NAME = u'arte.tv'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
def fetch_webpage(self, url):
self._downloader.increment_downloads()
request = urllib2.Request(url)
try:
self.report_download_webpage(url)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
except ValueError, err:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
return webpage
def grep_webpage(self, url, regex, regexFlags, matchTuples):
page = self.fetch_webpage(url)
mobj = re.search(regex, page, regexFlags)
info = {}
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
for (i, key, err) in matchTuples:
if mobj.group(i) is None:
self._downloader.trouble(err)
return
else:
info[key] = mobj.group(i)
return info
def extractLiveStream(self, url):
video_lang = url.split('/')[-4]
info = self.grep_webpage(
url,
r'src="(.*?/videothek_js.*?\.js)',
0,
[
(1, 'url', u'ERROR: Invalid URL: %s' % url)
]
)
http_host = url.split('/')[2]
next_url = 'http://%s%s' % (http_host, urllib.unquote(info.get('url')))
info = self.grep_webpage(
next_url,
r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
'(http://.*?\.swf).*?' +
'(rtmp://.*?)\'',
re.DOTALL,
[
(1, 'path', u'ERROR: could not extract video path: %s' % url),
(2, 'player', u'ERROR: could not extract video player: %s' % url),
(3, 'url', u'ERROR: could not extract video url: %s' % url)
]
)
video_url = u'%s/%s' % (info.get('url'), info.get('path'))
print u'rtmpdump --swfVfy \'%s\' --rtmp \'%s\' --live -o arte-live.mp4' % (info.get('player'), video_url)
def extractPlus7Stream(self, url):
video_lang = url.split('/')[-3]
info = self.grep_webpage(
url,
r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
0,
[
(1, 'url', u'ERROR: Invalid URL: %s' % url)
]
)
next_url = urllib.unquote(info.get('url'))
info = self.grep_webpage(
next_url,
r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
0,
[
(1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
]
)
next_url = urllib.unquote(info.get('url'))
info = self.grep_webpage(
next_url,
r'<video id="(.*?)".*?>.*?' +
'<name>(.*?)</name>.*?' +
'<dateVideo>(.*?)</dateVideo>.*?' +
'<url quality="hd">(.*?)</url>',
re.DOTALL,
[
(1, 'id', u'ERROR: could not extract video id: %s' % url),
(2, 'title', u'ERROR: could not extract video title: %s' % url),
(3, 'date', u'ERROR: could not extract video date: %s' % url),
(4, 'url', u'ERROR: could not extract video url: %s' % url)
]
)
return {
'id': info.get('id'),
'url': urllib.unquote(info.get('url')),
'uploader': u'arte.tv',
'upload_date': info.get('date'),
'title': info.get('title'),
'ext': u'mp4',
'format': u'NA',
'player_url': None,
}
def _real_extract(self, url):
video_id = url.split('/')[-1]
self.report_extraction(video_id)
if re.search(self._LIVE_URL, video_id) is not None:
self.extractLiveStream(url)
return
else:
info = self.extractPlus7Stream(url)
try:
# Process video information
self._downloader.process_info(info)
except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download video')
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
"""Generic last-resort information extractor.""" """Generic last-resort information extractor."""

View file

@ -351,6 +351,7 @@ def gen_extractors():
MixcloudIE(), MixcloudIE(),
StanfordOpenClassroomIE(), StanfordOpenClassroomIE(),
MTVIE(), MTVIE(),
ArteTvIE(),
GenericIE() GenericIE()
] ]