X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2FInfoExtractors.py;h=325c5ecd4c580018fd168f3812c3aafb885e5c57;hb=7da5556ac2985c246de0f0e4df982585577f44ba;hp=110ec834cfe34c060ab7a6163fc3108862070172;hpb=aed523ecc15febe787d919bba8f4ca3cb8c1abf2;p=youtube-dl
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 110ec834c..325c5ecd4 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -124,8 +124,8 @@ class InfoExtractor(object):
errnote = u'Unable to download webpage'
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
- def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
- """ Returns the data of the page as a string """
+ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns a tuple (page content as string, URL handle) """
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '')
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
@@ -142,7 +142,12 @@ class InfoExtractor(object):
self.to_screen(u'Dumping request to ' + url)
dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump)
- return webpage_bytes.decode(encoding, 'replace')
+ content = webpage_bytes.decode(encoding, 'replace')
+ return (content, urlh)
+
+ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the data of the page as a string """
+ return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
def to_screen(self, msg):
"""Print msg to screen, prefixing it with '[ie_name]'"""
@@ -206,7 +211,7 @@ class YoutubeIE(InfoExtractor):
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+ _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
@@ -422,7 +427,7 @@ class YoutubeIE(InfoExtractor):
# Log in
login_form_strs = {
- u'continue': u'http://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
+ u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
u'Email': username,
u'GALX': galx,
u'Passwd': password,
@@ -482,12 +487,12 @@ class YoutubeIE(InfoExtractor):
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
- url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
+ url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
video_id = self._extract_id(url)
# Get video webpage
self.report_video_webpage_download(video_id)
- url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
+ url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
request = compat_urllib_request.Request(url)
try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read()
@@ -779,7 +784,6 @@ class MetacafeIE(InfoExtractor):
'ext': video_extension.decode('utf-8'),
}]
-
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
@@ -1069,13 +1073,7 @@ class VimeoIE(InfoExtractor):
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(request, video_id)
# Now we begin extracting as much information as we can from what we
# retrieved. First we extract the information common to all extractors,
@@ -1682,10 +1680,6 @@ class YoutubePlaylistIE(InfoExtractor):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
-
def _real_extract(self, url):
# Extract playlist id
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
@@ -1699,14 +1693,8 @@ class YoutubePlaylistIE(InfoExtractor):
videos = []
while True:
- self.report_download_page(playlist_id, page_num)
-
url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
- try:
- page = compat_urllib_request.urlopen(url).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
try:
response = json.loads(page)
@@ -1745,10 +1733,6 @@ class YoutubeChannelIE(InfoExtractor):
_MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = u'youtube:channel'
- def report_download_page(self, channel_id, pagenum):
- """Report attempt to download channel page with given number."""
- self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
-
def extract_videos_from_page(self, page):
ids_in_page = []
for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page):
@@ -1768,14 +1752,9 @@ class YoutubeChannelIE(InfoExtractor):
video_ids = []
pagenum = 1
- self.report_download_page(channel_id, pagenum)
url = self._TEMPLATE_URL % (channel_id, pagenum)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, channel_id,
+ u'Downloading page #%s' % pagenum)
# Extract video identifiers
ids_in_page = self.extract_videos_from_page(page)
@@ -1786,14 +1765,9 @@ class YoutubeChannelIE(InfoExtractor):
while True:
pagenum = pagenum + 1
- self.report_download_page(channel_id, pagenum)
url = self._MORE_PAGES_URL % (pagenum, channel_id)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, channel_id,
+ u'Downloading page #%s' % pagenum)
page = json.loads(page)
@@ -1820,11 +1794,6 @@ class YoutubeUserIE(InfoExtractor):
_VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
IE_NAME = u'youtube:user'
- def report_download_page(self, username, start_index):
- """Report attempt to download user page."""
- self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
- (username, start_index, start_index + self._GDATA_PAGE_SIZE))
-
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
@@ -1844,15 +1813,10 @@ class YoutubeUserIE(InfoExtractor):
while True:
start_index = pagenum * self._GDATA_PAGE_SIZE + 1
- self.report_download_page(username, start_index)
-
- request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)
+ page = self._download_webpage(gdata_url, username,
+ u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE))
# Extract video identifiers
ids_in_page = []
@@ -1886,11 +1850,6 @@ class BlipTVUserIE(InfoExtractor):
_PAGE_SIZE = 12
IE_NAME = u'blip.tv:user'
- def report_download_page(self, username, pagenum):
- """Report attempt to download user page."""
- self.to_screen(u'user %s: Downloading video ids from page %d' %
- (username, pagenum))
-
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
@@ -1902,15 +1861,9 @@ class BlipTVUserIE(InfoExtractor):
page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
- request = compat_urllib_request.Request(url)
-
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- mobj = re.search(r'data-users-id="([^"]+)"', page)
- page_base = page_base % mobj.group(1)
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, username, u'Downloading user page')
+ mobj = re.search(r'data-users-id="([^"]+)"', page)
+ page_base = page_base % mobj.group(1)
# Download video ids using BlipTV Ajax calls. Result size per
@@ -1922,14 +1875,9 @@ class BlipTVUserIE(InfoExtractor):
pagenum = 1
while True:
- self.report_download_page(username, pagenum)
url = page_base + "&page=" + str(pagenum)
- request = compat_urllib_request.Request( url )
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % str(err))
- return
+ page = self._download_webpage(url, username,
+ u'Downloading video ids from page %d' % pagenum)
# Extract video identifiers
ids_in_page = []
@@ -2288,12 +2236,6 @@ class ComedyCentralIE(InfoExtractor):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
- def report_config_download(self, episode_id, media_id):
- self.to_screen(u'%s: Downloading configuration for %s' % (episode_id, media_id))
-
- def report_index_download(self, episode_id):
- self.to_screen(u'%s: Downloading show index' % episode_id)
-
def _print_formats(self, formats):
print('Available formats:')
for x in formats:
@@ -2327,24 +2269,15 @@ class ComedyCentralIE(InfoExtractor):
else:
epTitle = mobj.group('episode')
- req = compat_urllib_request.Request(url)
self.report_extraction(epTitle)
- try:
- htmlHandle = compat_urllib_request.urlopen(req)
- html = htmlHandle.read()
- webpage = html.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
if dlNewest:
url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.report_error(u'Invalid redirected URL: ' + url)
- return
+ raise ExtractorError(u'Invalid redirected URL: ' + url)
if mobj.group('episode') == '':
- self._downloader.report_error(u'Redirected URL is still not specific: ' + url)
- return
+ raise ExtractorError(u'Redirected URL is still not specific: ' + url)
epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:[^/]+)/(?P[^/?]+)[/?]?.*$'
IE_NAME = u'escapist'
- def report_config_download(self, showName):
- self.to_screen(u'%s: Downloading configuration' % showName)
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -2458,14 +2379,7 @@ class EscapistIE(InfoExtractor):
videoId = mobj.group('episode')
self.report_extraction(showName)
- try:
- webPage = compat_urllib_request.urlopen(url)
- webPageBytes = webPage.read()
- m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
- webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: ' + compat_str(err))
- return
+ webPage = self._download_webpage(url, showName)
descMatch = re.search('video|app)/ #If the page is only for videos or for a game
(?P\d+)/?
@@ -3625,18 +3487,17 @@ class WorldStarHipHopIE(InfoExtractor):
IE_NAME = u'WorldStarHipHop'
def _real_extract(self, url):
- _src_url = r"""(http://hw-videos.*(?:mp4|flv))"""
-
- webpage_src = compat_urllib_request.urlopen(url).read()
- webpage_src = webpage_src.decode('utf-8')
-
- mobj = re.search(_src_url, webpage_src)
+ _src_url = r'so\.addVariable\("file","(.*?)"\)'
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
+ webpage_src = self._download_webpage(url, video_id)
+
+ mobj = re.search(_src_url, webpage_src)
+
if mobj is not None:
- video_url = mobj.group()
+ video_url = mobj.group(1)
if 'mp4' in video_url:
ext = 'mp4'
else:
@@ -3988,12 +3849,13 @@ class KeekIE(InfoExtractor):
return [info]
class TEDIE(InfoExtractor):
- _VALID_URL=r'''http://www.ted.com/
+ _VALID_URL=r'''http://www\.ted\.com/
(
((?Pplaylists)/(?P\d+)) # We have a playlist
|
((?Ptalks)) # We have a simple talk
)
+ (/lang/(.*?))? # The url may contain the language
/(?P\w+) # Here goes the name and then ".html"
'''
@@ -4244,7 +4106,7 @@ class ARDIE(InfoExtractor):
return [info]
class TumblrIE(InfoExtractor):
- _VALID_URL = r'http://(?P.*?).tumblr.com/((post)|(video))/(?P\d*)/(.*?)'
+ _VALID_URL = r'http://(?P.*?)\.tumblr\.com/((post)|(video))/(?P\d*)/(.*?)'
def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url)
@@ -4254,7 +4116,7 @@ class TumblrIE(InfoExtractor):
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(url, video_id)
- re_video = r'src=\\x22(?Phttp://%s.tumblr.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P.*?)\\x22' % (blog, video_id)
+ re_video = r'src=\\x22(?Phttp://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage)
if video is None:
self.to_screen("No video founded")
@@ -4267,8 +4129,8 @@ class TumblrIE(InfoExtractor):
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
- re_title = r'(.*?) - (?P.*?)'
- title = unescapeHTML(re.search(re_title, webpage).group('title'))
+ re_title = r'(?P.*?)'
+ title = unescapeHTML(re.search(re_title, webpage, re.DOTALL).group('title'))
return [{'id': video_id,
'url': video_url,
@@ -4278,7 +4140,7 @@ class TumblrIE(InfoExtractor):
}]
class BandcampIE(InfoExtractor):
- _VALID_URL = r'http://.*?.bandcamp.com/track/(?P.*)'
+ _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P.*)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -4303,7 +4165,7 @@ class BandcampIE(InfoExtractor):
mp3_info = info[u'downloads'][u'mp3-320']
# If we try to use this url it says the link has expired
initial_url = mp3_info[u'url']
- re_url = r'(?Phttp://(.*?).bandcamp.com)/download/track\?enc=mp3-320&fsig=(?P.*?)&id=(?P.*?)&ts=(?P.*)$'
+ re_url = r'(?Phttp://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P.*?)&id=(?P.*?)&ts=(?P.*)$'
m_url = re.match(re_url, initial_url)
#We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js
@@ -4323,6 +4185,37 @@ class BandcampIE(InfoExtractor):
return [track_info]
+class RedTubeIE(InfoExtractor):
+ """Information Extractor for redtube"""
+ _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P[0-9]+)'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('id')
+ video_extension = 'mp4'
+ webpage = self._download_webpage(url, video_id)
+ self.report_extraction(video_id)
+ mobj = re.search(r'