uploader_id: Nickname or id of the video uploader.
location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
- subtitles: The .srt file contents.
+ subtitles: The subtitle file contents.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the data of the page as a string """
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)
+ if m:
+ encoding = m.group(1)
+ else:
+ encoding = 'utf-8'
webpage_bytes = urlh.read()
- return webpage_bytes.decode('utf-8', 'replace')
+ return webpage_bytes.decode(encoding, 'replace')
class YoutubeIE(InfoExtractor):
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
+ self._downloader.to_screen(u'[youtube] %s: Checking available subtitles' % video_id)
+
+ def report_video_subtitles_request(self, video_id, sub_lang, format):
+ """Report attempt to download video info webpage."""
+ self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
+
+ def report_video_subtitles_available(self, video_id, sub_lang_list):
+ """Report available subtitles."""
+ sub_lang = ",".join(list(sub_lang_list.keys()))
+ self._downloader.to_screen(u'[youtube] %s: Available subtitles for video: %s' % (video_id, sub_lang))
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
"""Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected')
- def _closed_captions_xml_to_srt(self, xml_string):
- srt = ''
- texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
- # TODO parse xml instead of regex
- for n, (start, dur_tag, dur, caption) in enumerate(texts):
- if not dur: dur = '4'
- start = float(start)
- 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 = unescapeHTML(caption)
- caption = unescapeHTML(caption) # double cycle, intentional
- srt += str(n+1) + '\n'
- srt += start + ' --> ' + end + '\n'
- srt += caption + '\n\n'
- return srt
-
- def _extract_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id):
self.report_video_subtitles_download(video_id)
request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
try:
- srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
- srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
- if not srt_lang_list:
- return (u'WARNING: video has no closed captions', None)
- if self._downloader.params.get('subtitleslang', False):
- srt_lang = self._downloader.params.get('subtitleslang')
- elif 'en' in srt_lang_list:
- srt_lang = 'en'
- else:
- srt_lang = list(srt_lang_list.keys())[0]
- if not srt_lang in srt_lang_list:
- return (u'WARNING: no closed captions found in the specified language', None)
+ sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
+ sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
+ if not sub_lang_list:
+ return (u'WARNING: video doesn\'t have subtitles', None)
+ return sub_lang_list
+
+ def _list_available_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ self.report_video_subtitles_available(video_id, sub_lang_list)
+
+ def _request_subtitle(self, sub_lang, sub_name, video_id, format):
+ self.report_video_subtitles_request(video_id, sub_lang, format)
params = compat_urllib_parse.urlencode({
- 'lang': srt_lang,
- 'name': srt_lang_list[srt_lang].encode('utf-8'),
+ 'lang': sub_lang,
+ 'name': sub_name,
'v': video_id,
+ 'fmt': format,
})
url = 'http://www.youtube.com/api/timedtext?' + params
try:
- srt_xml = compat_urllib_request.urlopen(url).read().decode('utf-8')
+ sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- if not srt_xml:
+ if not sub:
return (u'WARNING: Did not fetch video subtitles', None)
- return (None, self._closed_captions_xml_to_srt(srt_xml))
+ return (None, sub_lang, sub)
+
+ def _extract_subtitle(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ if self._downloader.params.get('subtitleslang', False):
+ sub_lang = self._downloader.params.get('subtitleslang')
+ elif 'en' in sub_lang_list:
+ sub_lang = 'en'
+ else:
+ sub_lang = list(sub_lang_list.keys())[0]
+ if not sub_lang in sub_lang_list:
+ return (u'WARNING: no closed captions found in the specified language "%s"' % sub_lang, None)
+
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ return [subtitle]
+
+ def _extract_all_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ subtitles = []
+ for sub_lang in sub_lang_list:
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ subtitles.append(subtitle)
+ return subtitles
def _print_formats(self, formats):
print('Available formats:')
if mobj is not None:
video_uploader_id = mobj.group(1)
else:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+ self._downloader.report_warning(u'unable to extract uploader nickname')
# title
if 'title' not in video_info:
# thumbnail image
if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ self._downloader.report_warning(u'unable to extract video thumbnail')
video_thumbnail = ''
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
else:
video_description = ''
- # closed captions
+ # subtitles
video_subtitles = None
+
if self._downloader.params.get('writesubtitles', False):
- (srt_error, video_subtitles) = self._extract_subtitles(video_id)
- if srt_error:
- self._downloader.trouble(srt_error)
+ video_subtitles = self._extract_subtitle(video_id)
+ if video_subtitles:
+ (sub_error, sub_lang, sub) = video_subtitles[0]
+ if sub_error:
+ self._downloader.trouble(sub_error)
+
+ if self._downloader.params.get('allsubtitles', False):
+ video_subtitles = self._extract_all_subtitles(video_id)
+ for video_subtitle in video_subtitles:
+ (sub_error, sub_lang, sub) = video_subtitle
+ if sub_error:
+ self._downloader.trouble(sub_error)
+
+ if self._downloader.params.get('listsubtitles', False):
+ sub_lang_list = self._list_available_subtitles(video_id)
+ return
if 'length_seconds' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video duration')
+ self._downloader.report_warning(u'unable to extract video duration')
video_duration = ''
else:
video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
# lookin for official user
mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
if mobj_official is None:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+ self._downloader.report_warning(u'unable to extract uploader nickname')
else:
video_uploader = mobj_official.group(1)
else:
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+ if not self._downloader.params.get('test', False):
+ self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
if self._test_redirect(url): return
video_id = url.split('/')[-1]
- request = compat_urllib_request.Request(url)
try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- 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(url, video_id)
except ValueError as err:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
webpage = self._download_webpage(webpage_url, video_id)
self.report_extraction(video_id)
- mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\' />',
+ mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\'',
webpage)
if mobj is None:
self._downloader.report_error(u'unable to extract media URL')
turls.append(finfo)
if len(turls) == 0:
- self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
+ self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
continue
if self._downloader.params.get('listformats', None):
'uploader': showName,
'upload_date': None,
'title': showName,
- 'ext': 'flv',
+ 'ext': 'mp4',
'thumbnail': imgUrl,
'description': description,
'player_url': playerUrl,
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
manifest_url = videoNode.findall('./file')[0].text
except IndexError:
- self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+ self._downloader.report_error(u'Invalid metadata XML file')
return
manifest_url += '?hdcore=2.10.3'
node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError as err:
- self._downloader.trouble(u'\nERROR: Invalid manifest file')
+ self._downloader.report_error(u'Invalid manifest file')
return
url_pr = compat_urllib_parse_urlparse(manifest_url)
'description': info['description'],
}]
+class SoundcloudSetIE(InfoExtractor):
+ """Information extractor for soundcloud.com sets
+ To access the media, the uid of the song and a stream token
+ must be extracted from the page source and the script must make
+ a request to media.soundcloud.com/crossdomain.xml. Then
+ the media can be grabbed by requesting from an url composed
+ of the stream token and uid
+ """
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
+ IE_NAME = u'soundcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_resolve(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ # extract uploader (which is in the url)
+ uploader = mobj.group(1)
+ # extract simple title (uploader + slug of song title)
+ slug_title = mobj.group(2)
+ simple_title = uploader + u'-' + slug_title
+
+ self.report_resolve('%s/sets/%s' % (uploader, slug_title))
+
+ url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
+ resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ request = compat_urllib_request.Request(resolv_url)
+ try:
+ info_json_bytes = compat_urllib_request.urlopen(request).read()
+ info_json = info_json_bytes.decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+ return
+
+ videos = []
+ info = json.loads(info_json)
+ if 'errors' in info:
+ for err in info['errors']:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err['error_message']))
+ return
+
+ for track in info['tracks']:
+ video_id = track['id']
+ self.report_extraction('%s/sets/%s' % (uploader, slug_title))
+
+ streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ request = compat_urllib_request.Request(streams_url)
+ try:
+ stream_json_bytes = compat_urllib_request.urlopen(request).read()
+ stream_json = stream_json_bytes.decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err))
+ return
+
+ streams = json.loads(stream_json)
+ mediaURL = streams['http_mp3_128_url']
+
+ videos.append({
+ 'id': video_id,
+ 'url': mediaURL,
+ 'uploader': track['user']['username'],
+ 'upload_date': track['created_at'],
+ 'title': track['title'],
+ 'ext': u'mp3',
+ 'description': track['description'],
+ })
+ return videos
+
class InfoQIE(InfoExtractor):
"""Information extractor for infoq.com"""
info['title'] = mdoc.findall('./title')[0].text
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
except IndexError:
- self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+ self._downloader.report_error(u'Invalid metadata XML file')
return
info['ext'] = info['url'].rpartition('.')[2]
return [info]
self._downloader.report_error(u'unable to find video information')
video_url = unescapeHTML(m.group('url'))
- m = re.search(r"class='player_page_h1'>\s+<a.*?>(?P<title>.*?)</a>", webpage)
+ m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
if not m:
self._downloader.trouble(u'Cannot find video title')
- title = unescapeHTML(m.group('title'))
+ title = clean_html(m.group('title'))
m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
if m:
}
return [info]
+class WorldStarHipHopIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+ 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)
+
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ if mobj is not None:
+ video_url = mobj.group()
+ if 'mp4' in video_url:
+ ext = 'mp4'
+ else:
+ ext = 'flv'
+ else:
+ self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+ return
+
+ _title = r"""<title>(.*)</title>"""
+
+ mobj = re.search(_title, webpage_src)
+
+ if mobj is not None:
+ title = mobj.group(1)
+ else:
+ title = 'World Start Hip Hop - %s' % time.ctime()
+
+ _thumbnail = r"""rel="image_src" href="(.*)" />"""
+ mobj = re.search(_thumbnail, webpage_src)
+
+ # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+ if mobj is not None:
+ thumbnail = mobj.group(1)
+ else:
+ _title = r"""candytitles.*>(.*)</span>"""
+ mobj = re.search(_title, webpage_src)
+ if mobj is not None:
+ title = mobj.group(1)
+ thumbnail = None
+
+ results = [{
+ 'id': video_id,
+ 'url' : video_url,
+ 'title' : title,
+ 'thumbnail' : thumbnail,
+ 'ext' : ext,
+ }]
+ return results
+
class RBMARadioIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
webpage = self._download_webpage(url, video_id)
m = re.search(r'<meta property="og:title" content="(?P<title>.+)"', webpage)
title = unescapeHTML(m.group('title'))
- m = re.search(r'<div class="bio-names-and-report">[\s\n]+<h4>(?P<uploader>\w+)</h4>', webpage)
- uploader = unescapeHTML(m.group('uploader'))
+ m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
+ uploader = clean_html(m.group('uploader'))
info = {
- 'id':video_id,
- 'url':video_url,
+ 'id': video_id,
+ 'url': video_url,
'ext': 'mp4',
'title': title,
'thumbnail': thumbnail,
videoName=m.group('name')
webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName)
# If the url includes the language we get the title translated
- title_RE=r'<h1><span id="altHeadline" >(?P<title>.*)</span></h1>'
+ title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>'
title=re.search(title_RE, webpage).group('title')
info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
"id":(?P<videoID>[\d]+).*?
}
return [info]
+class SpiegelIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find title')
+ video_title = unescapeHTML(m.group(1))
+
+ xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
+ xml_code = self._download_webpage(xml_url, video_id,
+ note=u'Downloading XML', errnote=u'Failed to download XML')
+
+ idoc = xml.etree.ElementTree.fromstring(xml_code)
+ last_type = idoc[-1]
+ filename = last_type.findall('./filename')[0].text
+ duration = float(last_type.findall('./duration')[0].text)
+
+ video_url = 'http://video2.spiegel.de/flash/' + filename
+ video_ext = filename.rpartition('.')[2]
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': video_title,
+ 'duration': duration,
+ }
+ return [info]
+
+class LiveLeakIE(InfoExtractor):
+
+ _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+ IE_NAME = u'liveleak'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group('video_id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'file: "(.*?)",', webpage)
+ if not m:
+ self._downloader.report_error(u'unable to find video url')
+ return
+ video_url = m.group(1)
+
+ m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
+ if not m:
+ self._downloader.trouble(u'Cannot find video title')
+ title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
+
+ m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+ if m:
+ desc = unescapeHTML(m.group('desc'))
+ else:
+ desc = None
+
+ m = re.search(r'By:.*?(\w+)</a>', webpage)
+ if m:
+ uploader = clean_html(m.group(1))
+ else:
+ uploader = None
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': desc,
+ 'uploader': uploader
+ }
+
+ return [info]
+
+
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
EscapistIE(),
CollegeHumorIE(),
XVideosIE(),
+ SoundcloudSetIE(),
SoundcloudIE(),
InfoQIE(),
MixcloudIE(),
GooglePlusIE(),
ArteTvIE(),
NBAIE(),
+ WorldStarHipHopIE(),
JustinTVIE(),
FunnyOrDieIE(),
SteamIE(),
KeekIE(),
TEDIE(),
MySpassIE(),
+ SpiegelIE(),
+ LiveLeakIE(),
GenericIE()
]
-
-
projects / youtube-dl / blobdiff