blip.tv: Handle direct URLs (Thanks to Bahman)

This commit is contained in:
Philipp Hagemeister 2011-09-27 21:42:15 +02:00
parent 9baa2ef53b
commit 54f329fe93

View file

@ -766,7 +766,8 @@ class FileDownloader(object):
try:
infof = open(infofn, 'wb')
try:
json.dump(info_dict, infof)
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
json.dump(json_info_dict, infof)
finally:
infof.close()
except (OSError, IOError):
@ -905,6 +906,8 @@ class FileDownloader(object):
while count <= retries:
# Establish connection
try:
if count == 0 and 'urlhandle' in info_dict:
data = info_dict['urlhandle']
data = urllib2.urlopen(request)
break
except (urllib2.HTTPError, ), err:
@ -2895,7 +2898,11 @@ class BlipTVIE(InfoExtractor):
def report_extraction(self, file_id):
"""Report information extraction."""
self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
def report_direct_download(self, title):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
def _simplify_title(self, title):
res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
@ -2915,43 +2922,64 @@ class BlipTVIE(InfoExtractor):
json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
request = urllib2.Request(json_url)
self.report_extraction(mobj.group(1))
info = None
try:
json_code = urllib2.urlopen(request).read()
urlh = urllib2.urlopen(request)
if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
basename = url.split('/')[-1]
title,ext = os.path.splitext(basename)
ext = ext.replace('.', '')
self.report_direct_download(title)
info = {
'id': title,
'url': url,
'title': title,
'stitle': self._simplify_title(title),
'ext': ext,
'urlhandle': urlh
}
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
return
try:
json_data = json.loads(json_code)
if 'Post' in json_data:
data = json_data['Post']
else:
data = json_data
if info is None: # Regular URL
try:
json_code = urlh.read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
return
upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
video_url = data['media']['url']
umobj = re.match(self._URL_EXT, video_url)
if umobj is None:
raise ValueError('Can not determine filename extension')
ext = umobj.group(1)
try:
json_data = json.loads(json_code)
if 'Post' in json_data:
data = json_data['Post']
else:
data = json_data
self._downloader.increment_downloads()
upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
video_url = data['media']['url']
umobj = re.match(self._URL_EXT, video_url)
if umobj is None:
raise ValueError('Can not determine filename extension')
ext = umobj.group(1)
info = {
'id': data['item_id'],
'url': video_url,
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
'stitle': self._simplify_title(data['title']),
'ext': ext,
'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
'description': data['description'],
'player_url': data['embedUrl']
}
except (ValueError,KeyError), err:
self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
return
info = {
'id': data['item_id'],
'url': video_url,
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
'stitle': self._simplify_title(data['title']),
'ext': ext,
'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
'description': data['description'],
'player_url': data['embedUrl']
}
except (ValueError,KeyError), err:
self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
return
self._downloader.increment_downloads()
try:
self._downloader.process_info(info)
@ -3017,7 +3045,6 @@ class MyVideoIE(InfoExtractor):
video_title = sanitize_title(video_title)
try:
print(video_url)
self._downloader.process_info({
'id': video_id,
'url': video_url,