'''
_TESTS = [{
'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html',
- 'md5': '4ea1dada91e4174b53dac2bb8ace429d',
+ 'md5': 'fc94ac279feebbce69f21c0c6ee82810',
'info_dict': {
'id': '102',
'ext': 'mp4',
'title': 'The illusion of consciousness',
'description': ('Philosopher Dan Dennett makes a compelling '
- 'argument that not only don\'t we understand our own '
- 'consciousness, but that half the time our brains are '
- 'actively fooling us.'),
+ 'argument that not only don\'t we understand our own '
+ 'consciousness, but that half the time our brains are '
+ 'actively fooling us.'),
'uploader': 'Dan Dennett',
'width': 854,
+ 'duration': 1308,
}
}, {
'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms',
'thumbnail': 're:^https?://.+\.jpg',
'description': 'Adaptive, intelligent, and consistent, algorithms are emerging as the ultimate app for everything from matching consumers to products to assessing medical diagnoses. Vishal Sikka shares his appreciation for the algorithm, charting both its inherent beauty and its growing power.',
}
+ }, {
+ 'url': 'http://www.ted.com/talks/gabby_giffords_and_mark_kelly_be_passionate_be_courageous_be_your_best',
+ 'info_dict': {
+ 'id': '1972',
+ 'ext': 'mp4',
+ 'title': 'Be passionate. Be courageous. Be your best.',
+ 'uploader': 'Gabby Giffords and Mark Kelly',
+ 'description': 'md5:5174aed4d0f16021b704120360f72b92',
+ 'duration': 1128,
+ },
+ }, {
+ 'url': 'http://www.ted.com/playlists/who_are_the_hackers',
+ 'info_dict': {
+ 'id': '10',
+ 'title': 'Who are the hackers?',
+ },
+ 'playlist_mincount': 6,
+ }, {
+ # contains a youtube video
+ 'url': 'https://www.ted.com/talks/douglas_adams_parrots_the_universe_and_everything',
+ 'add_ie': ['Youtube'],
+ 'info_dict': {
+ 'id': '_ZG8HBuDjgc',
+ 'ext': 'mp4',
+ 'title': 'Douglas Adams: Parrots the Universe and Everything',
+ 'description': 'md5:01ad1e199c49ac640cb1196c0e9016af',
+ 'uploader': 'University of California Television (UCTV)',
+ 'uploader_id': 'UCtelevision',
+ 'upload_date': '20080522',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}]
_NATIVE_FORMATS = {
def _extract_info(self, webpage):
info_json = self._search_regex(r'q\("\w+.init",({.+})\)</script>',
- webpage, 'info json')
+ webpage, 'info json')
return json.loads(info_json)
def _real_extract(self, url):
'''Returns the videos of the playlist'''
webpage = self._download_webpage(url, name,
- 'Downloading playlist webpage')
+ 'Downloading playlist webpage')
info = self._extract_info(webpage)
playlist_info = info['playlist']
playlist_entries = [
- self.url_result(u'http://www.ted.com/talks/' + talk['slug'], self.ie_key())
+ self.url_result('http://www.ted.com/talks/' + talk['slug'], self.ie_key())
for talk in info['talks']
]
return self.playlist_result(
talk_info = self._extract_info(webpage)['talks'][0]
+ if talk_info.get('external') is not None:
+ self.to_screen('Found video from %s' % talk_info['external']['service'])
+ return {
+ '_type': 'url',
+ 'url': talk_info['external']['uri'],
+ }
+
formats = [{
'url': format_url,
'format_id': format_id,
'format': format_id,
- } for (format_id, format_url) in talk_info['nativeDownloads'].items()]
- for f in formats:
- finfo = self._NATIVE_FORMATS.get(f['format_id'])
- if finfo:
- f.update(finfo)
+ } for (format_id, format_url) in talk_info['nativeDownloads'].items() if format_url is not None]
+ if formats:
+ for f in formats:
+ finfo = self._NATIVE_FORMATS.get(f['format_id'])
+ if finfo:
+ f.update(finfo)
+ else:
+ # Use rtmp downloads
+ formats = [{
+ 'format_id': f['name'],
+ 'url': talk_info['streamer'],
+ 'play_path': f['file'],
+ 'ext': 'flv',
+ 'width': f['width'],
+ 'height': f['height'],
+ 'tbr': f['bitrate'],
+ } for f in talk_info['resources']['rtmp']]
self._sort_formats(formats)
video_id = compat_str(talk_info['id'])
thumbnail = 'http://' + thumbnail
return {
'id': video_id,
- 'title': talk_info['title'],
+ 'title': talk_info['title'].strip(),
'uploader': talk_info['speaker'],
'thumbnail': thumbnail,
'description': self._og_search_description(webpage),
'subtitles': video_subtitles,
'formats': formats,
+ 'duration': talk_info.get('duration'),
}
def _get_available_subtitles(self, video_id, talk_info):
sub_lang_list[l] = url
return sub_lang_list
else:
- self._downloader.report_warning(u'video doesn\'t have subtitles')
+ self._downloader.report_warning('video doesn\'t have subtitles')
return {}
def _watch_info(self, url, name):
title = self._html_search_regex(
r"(?s)<h1(?:\s+class='[^']+')?>(.+?)</h1>", webpage, 'title')
description = self._html_search_regex(
- r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>',
+ [
+ r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>',
+ r'(?s)<p><strong>About this talk:</strong>\s+(.*?)</p>',
+ ],
webpage, 'description', fatal=False)
return {
projects / youtube-dl / blobdiff