import urllib
import urllib2
import email.utils
+import xml.etree.ElementTree
+from urlparse import parse_qs
try:
import cStringIO as StringIO
except ImportError:
import StringIO
-# parse_qs was moved from the cgi module to the urlparse module recently.
-try:
- from urlparse import parse_qs
-except ImportError:
- from cgi import parse_qs
-
-try:
- import lxml.etree
-except ImportError:
- pass # Handled below
-
-try:
- import xml.etree.ElementTree
-except ImportError: # Python<2.5: Not officially supported, but let it slip
- warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.')
-
from utils import *
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
- _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
- _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
+ _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
+ _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'43': 'webm',
'44': 'webm',
'45': 'webm',
+ '46': 'webm',
}
_video_dimensions = {
'5': '240x400',
'43': '360x640',
'44': '480x854',
'45': '720x1280',
+ '46': '1080x1920',
}
IE_NAME = u'youtube'
end = start + float(dur)
start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
- caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption)
- caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional
+ caption = unescapeHTML(caption)
+ caption = unescapeHTML(caption) # double cycle, inentional
srt += str(n) + '\n'
srt += start + ' --> ' + end + '\n'
srt += caption + '\n\n'
pass
# description
- try:
- lxml.etree
- except NameError:
- video_description = u'No description available.'
- mobj = re.search(r'<meta name="description" content="(.*?)">', video_webpage)
- if mobj is not None:
- video_description = mobj.group(1).decode('utf-8')
- else:
- html_parser = lxml.etree.HTMLParser(encoding='utf-8')
- vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser)
- video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
- # TODO use another parser
+ video_description = get_element_by_id("eow-description", video_webpage.decode('utf8'))
+ if video_description: video_description = clean_html(video_description)
+ else: video_description = ''
# closed captions
video_subtitles = None
self._downloader.trouble(u'ERROR: Unable to extract media URL')
return
video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
- video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
+ video_url = unescapeHTML(video_url)
return [{
'id': video_id.decode('utf-8'),
video_thumbnail = config["video"]["thumbnail"]
# Extract video description
- try:
- lxml.etree
- except NameError:
- video_description = u'No description available.'
- mobj = re.search(r'<meta name="description" content="(.*?)" />', webpage, re.MULTILINE)
- if mobj is not None:
- video_description = mobj.group(1)
- else:
- html_parser = lxml.etree.HTMLParser()
- vwebpage_doc = lxml.etree.parse(StringIO.StringIO(webpage), html_parser)
- video_description = u''.join(vwebpage_doc.xpath('id("description")//text()')).strip()
- # TODO use another parser
+ video_description = get_element_by_id("description", webpage.decode('utf8'))
+ if video_description: video_description = clean_html(video_description)
+ else: video_description = ''
# Extract upload date
video_upload_date = u'NA'
data = json_data['Post']
else:
data = json_data
-
+
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,
def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
-
+
def report_config_download(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
- description = htmlParser.unescape(descMatch.group(1))
+ description = unescapeHTML(descMatch.group(1))
imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
- imgUrl = htmlParser.unescape(imgMatch.group(1))
+ imgUrl = unescapeHTML(imgMatch.group(1))
playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
- playerUrl = htmlParser.unescape(playerUrlMatch.group(1))
+ playerUrl = unescapeHTML(playerUrlMatch.group(1))
configUrlMatch = re.search('config=(.*)$', playerUrl)
configUrl = urllib2.unquote(configUrlMatch.group(1))
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
url_list = jsonData[fmt][bitrate]
except TypeError: # we have no bitrate info.
url_list = jsonData[fmt]
-
return url_list
def check_urls(self, url_list):
info = {
'id': simplify_title(course + '_' + video),
}
-
+
self.report_extraction(info['id'])
baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
xmlUrl = baseUrl + video + '.xml'
info['format'] = info['ext']
return [info]
elif mobj.group('course'): # A course page
- unescapeHTML = HTMLParser.HTMLParser().unescape
-
course = mobj.group('course')
info = {
'id': simplify_title(course),
return results
else: # Root page
- unescapeHTML = HTMLParser.HTMLParser().unescape
-
info = {
'id': 'Stanford OpenClassroom',
'type': 'playlist',
projects / youtube-dl / blobdiff