"""Information Extractor class.
Information extractors are the classes that, given a URL, extract
- information from the video (or videos) the URL refers to. This
- information includes the real video URL, the video title and simplified
- title, author and others. The information is stored in a dictionary
- which is then passed to the FileDownloader. The FileDownloader
- processes this information possibly downloading the video to the file
- system, among other possible outcomes. The dictionaries must include
- the following fields:
-
- id: Video identifier.
- url: Final video URL.
- uploader: Nickname of the video uploader.
- title: Literal title.
- ext: Video filename extension.
- format: Video format.
- player_url: SWF Player URL (may be None).
-
- The following fields are optional. Their primary purpose is to allow
- youtube-dl to serve as the backend for a video search function, such
- as the one in youtube2mp3. They are only used when their respective
- forced printing functions are called:
-
- thumbnail: Full URL to a video thumbnail image.
- description: One-line video description.
+ information about the video (or videos) the URL refers to. This
+ information includes the real video URL, the video title, author and
+ others. The information is stored in a dictionary which is then
+ passed to the FileDownloader. The FileDownloader processes this
+ information possibly downloading the video to the file system, among
+ other possible outcomes.
+
+ The dictionaries must include the following fields:
+
+ id: Video identifier.
+ url: Final video URL.
+ uploader: Nickname of the video uploader, unescaped.
+ upload_date: Video upload date (YYYYMMDD).
+ title: Video title, unescaped.
+ ext: Video filename extension.
+
+ The following fields are optional:
+
+ format: The video format, defaults to ext (used for --get-format)
+ thumbnail: Full URL to a video thumbnail image.
+ description: One-line video description.
+ player_url: SWF Player URL (used for rtmpdump).
+ subtitles: The .srt file contents.
+ urlhandle: [internal] The urlHandle to be used to download the file,
+ like returned by urllib2.urlopen
+
+ The fields should all be Unicode strings.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be added to the list of extractors.
+
+ _real_extract() must return a *list* of information dictionaries as
+ described above.
+
+ Finally, the _WORKING attribute should be set to False for broken IEs
+ in order to warn the users and skip the tests.
"""
_ready = False
_downloader = None
+ _WORKING = True
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""
"""Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url) is not None
+ def working(self):
+ """Getter method for _WORKING."""
+ return self._WORKING
+
def initialize(self):
"""Initializes an instance (authentication, etc)."""
if not self._ready:
video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
# upload date
- upload_date = u'NA'
+ upload_date = None
mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
+ video_format = '{} - {}'.format(format_param.decode('utf-8') if format_param else video_extension.decode('utf-8'),
+ self._video_dimensions.get(format_param, '???'))
+
results.append({
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
'upload_date': upload_date,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'format': video_format,
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'player_url': player_url,
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
return
video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
- video_uploader = u'NA'
+ video_uploader = None
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
if mobj is None:
# lookin for official user
else:
video_uploader = mobj.group(1)
- video_upload_date = u'NA'
+ video_upload_date = None
mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
if mobj is not None:
video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
'upload_date': video_upload_date,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
return [{
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
- 'uploader': u'NA',
- 'upload_date': u'NA',
+ 'uploader': None,
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
'id': video_id.decode('utf-8'),
'url': video_url,
'uploader': video_uploader,
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
- 'thumbnail': video_thumbnail,
- 'player_url': None,
}]
else: video_description = ''
# Extract upload date
- video_upload_date = u'NA'
+ video_upload_date = None
mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage)
if mobj is not None:
video_upload_date = mobj.group(1)
'ext': video_extension,
'thumbnail': video_thumbnail,
'description': video_description,
- 'player_url': None,
}]
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
return [{
'id': file_id.decode('utf-8'),
'url': file_url.decode('utf-8'),
- 'uploader': u'NA',
- 'upload_date': u'NA',
+ 'uploader': None,
+ 'upload_date': None,
'title': file_title,
'ext': file_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
+ _WORKING = False
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
_NETRC_MACHINE = 'facebook'
video_thumbnail = video_info['thumbnail']
# upload date
- upload_date = u'NA'
+ upload_date = None
if 'upload_date' in video_info:
upload_time = video_info['upload_date']
timetuple = email.utils.parsedate_tz(upload_time)
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description.decode('utf-8'),
- 'player_url': None,
})
return results
info = {
'id': title,
'url': url,
+ 'uploader': None,
+ 'upload_date': None,
'title': title,
'ext': ext,
'urlhandle': urlh
return [{
'id': video_id,
'url': video_url,
- 'uploader': u'NA',
- 'upload_date': u'NA',
+ 'uploader': None,
+ 'upload_date': None,
'title': video_title,
'ext': u'flv',
- 'format': u'NA',
- 'player_url': None,
}]
class ComedyCentralIE(InfoExtractor):
'upload_date': None,
'title': showName,
'ext': 'flv',
- 'format': 'flv',
'thumbnail': imgUrl,
'description': description,
'player_url': playerUrl,
info = {
'id': video_id,
'internal_id': internal_video_id,
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_extraction(video_id)
info['url'] = videoNode.findall('./file')[0].text
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
info['ext'] = info['url'].rpartition('.')[2]
- info['format'] = info['ext']
except IndexError:
self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
return
'upload_date': None,
'title': video_title,
'ext': 'flv',
- 'format': 'flv',
'thumbnail': video_thumbnail,
'description': None,
- 'player_url': None,
}
return [info]
'upload_date': upload_date,
'title': title,
'ext': u'mp3',
- 'format': u'NA',
- 'player_url': None,
'description': description.decode('utf-8')
}]
'uploader': None,
'upload_date': None,
'title': video_title,
- 'ext': extension,
- 'format': extension, # Extension is always(?) mp4, but seems to be flv
+ 'ext': extension, # Extension is always(?) mp4, but seems to be flv
'thumbnail': None,
'description': video_description,
- 'player_url': None,
}
return [info]
'id': file_id.decode('utf-8'),
'url': file_url.decode('utf-8'),
'uploader': uploader.decode('utf-8'),
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': json_data['name'],
'ext': file_url.split('.')[-1].decode('utf-8'),
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
video = mobj.group('video')
info = {
'id': course + '_' + video,
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_extraction(info['id'])
self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
return
info['ext'] = info['url'].rpartition('.')[2]
- info['format'] = info['ext']
return [info]
elif mobj.group('course'): # A course page
course = mobj.group('course')
info = {
'id': course,
'type': 'playlist',
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_download_webpage(info['id'])
info = {
'id': 'Stanford OpenClassroom',
'type': 'playlist',
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_download_webpage(info['id'])
'id': video_id,
'url': video_url,
'uploader': performer,
+ 'upload_date': None,
'title': video_title,
'ext': ext,
'format': format,
'id': '%s_part%02d' % (video_id, index),
'url': download_url,
'uploader': None,
+ 'upload_date': None,
'title': video_title,
'ext': ext,
- 'format': u'NA'
}
files_info.append(info)
return
video_thumbnail = result.group(1).decode('utf-8')
- info = {'id': video_id,
- 'url': video_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': 'flv',
- 'format': 'flv',
- 'thumbnail': video_thumbnail,
- 'description': None,
- 'player_url': None}
-
- return [info]
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'thumbnail': video_thumbnail,
+ 'description': None,
+ }]
class GooglePlusIE(InfoExtractor):
return
# Extract update date
- upload_date = u'NA'
+ upload_date = None
pattern = 'title="Timestamp">(.*?)</a>'
mobj = re.search(pattern, webpage)
if mobj:
self.report_date(upload_date)
# Extract uploader
- uploader = u'NA'
+ uploader = None
pattern = r'rel\="author".*?>(.*?)</a>'
mobj = re.search(pattern, webpage)
if mobj:
'upload_date': upload_date.decode('utf-8'),
'title': video_title.decode('utf-8'),
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
projects / youtube-dl / commitdiff