X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=325c5ecd4c580018fd168f3812c3aafb885e5c57;hb=7da5556ac2985c246de0f0e4df982585577f44ba;hp=14a1d6523f4834ebcd85334d90b256dc6184f916;hpb=9e1cf0c2004563015d69c5a01aa419c4b70ad696;p=youtube-dl
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 14a1d6523..325c5ecd4 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -114,8 +114,8 @@ class InfoExtractor(object):
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the response handle """
if note is None:
- note = u'Downloading video webpage'
- if note is not False:
+ self.report_download_webpage(video_id)
+ elif note is not False:
self.to_screen(u'%s: %s' % (video_id, note))
try:
return compat_urllib_request.urlopen(url_or_request)
@@ -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]'"""
@@ -152,6 +157,10 @@ class InfoExtractor(object):
"""Report information extraction."""
self.to_screen(u'%s: Extracting information' % id_or_name)
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self.to_screen(u'%s: Downloading webpage' % video_id)
+
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self.to_screen(u'Confirming age')
@@ -202,7 +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=([^&]+)'
@@ -418,7 +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,
@@ -478,12 +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()
@@ -558,19 +567,18 @@ class YoutubeIE(InfoExtractor):
mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
- for expression in format_expressions:
- try:
- upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
- except:
- pass
+ upload_date = unified_strdate(upload_date)
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_description:
video_description = clean_html(video_description)
else:
- video_description = ''
+ fd_mobj = re.search(r'https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)'
IE_NAME = u'vimeo'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self.to_screen(u'%s: Downloading webpage' % video_id)
-
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
@@ -1101,13 +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,
@@ -1119,7 +1085,10 @@ class VimeoIE(InfoExtractor):
config = webpage.split(' = {config:')[1].split(',assets:')[0]
config = json.loads(config)
except:
- self._downloader.report_error(u'unable to extract info section')
+ if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
+ self._downloader.report_error(u'The author has restricted the access to this video, try with the "--referer" option')
+ else:
+ self._downloader.report_error(u'unable to extract info section')
return
# Extract title
@@ -1196,13 +1165,6 @@ class ArteTvIE(InfoExtractor):
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.to_screen(u'%s: Downloading webpage' % video_id)
-
def fetch_webpage(self, url):
request = compat_urllib_request.Request(url)
try:
@@ -1227,7 +1189,7 @@ class ArteTvIE(InfoExtractor):
for (i, key, err) in matchTuples:
if mobj.group(i) is None:
- self._downloader.trouble(err)
+ self._downloader.report_error(err)
return
else:
info[key] = mobj.group(i)
@@ -1241,7 +1203,7 @@ class ArteTvIE(InfoExtractor):
r'src="(.*?/videothek_js.*?\.js)',
0,
[
- (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ (1, 'url', u'Invalid URL: %s' % url)
]
)
http_host = url.split('/')[2]
@@ -1253,9 +1215,9 @@ class ArteTvIE(InfoExtractor):
'(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)
+ (1, 'path', u'could not extract video path: %s' % url),
+ (2, 'player', u'could not extract video player: %s' % url),
+ (3, 'url', u'could not extract video url: %s' % url)
]
)
video_url = u'%s/%s' % (info.get('url'), info.get('path'))
@@ -1267,7 +1229,7 @@ class ArteTvIE(InfoExtractor):
r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
0,
[
- (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ (1, 'url', u'Invalid URL: %s' % url)
]
)
next_url = compat_urllib_parse.unquote(info.get('url'))
@@ -1276,7 +1238,7 @@ class ArteTvIE(InfoExtractor):
r'