allsubtitles: Downloads all the subtitles of the video
listsubtitles: Lists all available subtitles for the video
subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt)
- subtitleslang: Language of the subtitles to download
+ subtitleslangs: List of languages of the subtitles to download
keepvideo: Keep the video file after post-processing
daterange: A DateRange object, download only if the upload_date is in the range.
skip_download: Skip the actual download of the video file
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
+ self._ies_instances = {}
self._pps = []
self._progress_hooks = []
self._download_retcode = 0
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
+ self._ies_instances[ie.ie_key()] = ie
ie.set_downloader(self)
+ def get_info_extractor(self, ie_key):
+ """
+ Get an instance of an IE with name ie_key, it will try to get one from
+ the _ies list, if there's no instance it will create a new one and add
+ it to the extractor list.
+ """
+ ie = self._ies_instances.get(ie_key)
+ if ie is None:
+ ie = get_info_extractor(ie_key)()
+ self.add_info_extractor(ie)
+ return ie
+
def add_default_info_extractors(self):
"""
Add the InfoExtractors returned by gen_extractors to the end of the list
self.report_error(u'Erroneous output template')
return None
except ValueError as err:
- self.report_error(u'Insufficient system charset ' + repr(preferredencoding()))
+ self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')')
return None
def _match_entry(self, info_dict):
'''
if ie_key:
- ie = get_info_extractor(ie_key)()
- ie.set_downloader(self)
- ies = [ie]
+ ies = [self.get_info_extractor(ie_key)]
else:
ies = self._ies
result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
if result_type == 'video':
+ ie_result.update(extra_info)
if 'playlist' not in ie_result:
# It isn't part of a playlist
ie_result['playlist'] = None
if self.params.get('forceid', False):
compat_print(info_dict['id'])
if self.params.get('forceurl', False):
- compat_print(info_dict['url'])
+ # For RTMP URLs, also include the playpath
+ compat_print(info_dict['url'] + info_dict.get('play_path', u''))
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
compat_print(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and 'description' in info_dict:
self.report_error(u'Cannot write description file ' + descfn)
return
- if (self.params.get('writesubtitles', False) or self.params.get('writeautomaticsub')) and 'subtitles' in info_dict and info_dict['subtitles']:
+ subtitles_are_requested = any([self.params.get('writesubtitles', False),
+ self.params.get('writeautomaticsub'),
+ self.params.get('allsubtitles', False)])
+
+ if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']:
# subtitles download errors are already managed as troubles in relevant IE
# that way it will silently go on when used with unsupporting IE
- subtitle = info_dict['subtitles'][0]
- (sub_error, sub_lang, sub) = subtitle
+ subtitles = info_dict['subtitles']
sub_format = self.params.get('subtitlesformat')
- if sub_error:
- self.report_warning("Some error while getting the subtitles")
- else:
+ for sub_lang in subtitles.keys():
+ sub = subtitles[sub_lang]
+ if sub is None:
+ continue
try:
- sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
+ sub_filename = subtitles_filename(filename, sub_lang, sub_format)
self.report_writesubtitles(sub_filename)
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
- subfile.write(sub)
+ subfile.write(sub)
except (OSError, IOError):
self.report_error(u'Cannot write subtitles file ' + descfn)
return
- if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
- subtitles = info_dict['subtitles']
- sub_format = self.params.get('subtitlesformat')
- for subtitle in subtitles:
- (sub_error, sub_lang, sub) = subtitle
- if sub_error:
- self.report_warning("Some error while getting the subtitles")
- else:
- try:
- sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
- self.report_writesubtitles(sub_filename)
- with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
- subfile.write(sub)
- except (OSError, IOError):
- self.report_error(u'Cannot write subtitles file ' + descfn)
- return
-
if self.params.get('writeinfojson', False):
infofn = filename + u'.info.json'
self.report_writeinfojson(infofn)
return
if self.params.get('writethumbnail', False):
- if 'thumbnail' in info_dict:
- thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2]
- if not thumb_format:
- thumb_format = 'jpg'
+ if info_dict.get('thumbnail') is not None:
+ thumb_format = determine_ext(info_dict['thumbnail'], u'jpg')
thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
(info_dict['extractor'], info_dict['id']))
try:
success = self.fd._do_download(filename, info_dict)
except (OSError, IOError) as err:
- raise UnavailableVideoError()
+ raise UnavailableVideoError(err)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_error(u'unable to download video data: %s' % str(err))
return
# No clear decision yet, let IE decide
keep_video = keep_video_wish
except PostProcessingError as e:
- self.to_stderr(u'ERROR: ' + e.msg)
+ self.report_error(e.msg)
if keep_video is False and not self.params.get('keepvideo', False):
try:
self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename)
clean_html,
compiled_regex_type,
ExtractorError,
+ unescapeHTML,
)
class InfoExtractor(object):
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 subtitle file contents.
+ subtitles: The subtitle file contents as a dictionary in the format
+ {language: subtitles}.
view_count: How many users have watched the video on the platform.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url) is not None
+
+ # This does not use has/getattr intentionally - we want to know whether
+ # we have cached the regexp for *this* class, whereas getattr would also
+ # match the superclass
+ if '_VALID_URL_RE' not in cls.__dict__:
+ cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+ return cls._VALID_URL_RE.match(url) is not None
@classmethod
def working(cls):
"""Real extraction process. Redefine in subclasses."""
pass
+ @classmethod
+ def ie_key(cls):
+ """A string for getting the InfoExtractor with get_info_extractor"""
+ return cls.__name__[:-2]
+
@property
def IE_NAME(self):
return type(self).__name__[:-2]
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
if errnote is None:
errnote = u'Unable to download webpage'
- raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+ raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
""" Returns a tuple (page content as string, URL handle) """
+
+ # Strip hashes from the URL (#1038)
+ if isinstance(url_or_request, (compat_str, str)):
+ url_or_request = url_or_request.partition('#')[0]
+
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)
self.to_screen(u'Logging in')
#Methods for following #608
- #They set the correct value of the '_type' key
- def video_result(self, video_info):
- """Returns a video"""
- video_info['_type'] = 'video'
- return video_info
def url_result(self, url, ie=None):
"""Returns a url that points to a page that should be processed"""
#TODO: ie should be the class used for getting the info
return (username, password)
+ # Helper functions for extracting OpenGraph info
+ @staticmethod
+ def _og_regex(prop):
+ return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
+
+ def _og_search_property(self, prop, html, name=None, **kargs):
+ if name is None:
+ name = 'OpenGraph %s' % prop
+ escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ return unescapeHTML(escaped)
+
+ def _og_search_thumbnail(self, html, **kargs):
+ return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
+
+ def _og_search_description(self, html, **kargs):
+ return self._og_search_property('description', html, fatal=False, **kargs)
+
+ def _og_search_title(self, html, **kargs):
+ return self._og_search_property('title', html, **kargs)
+
+ def _og_search_video_url(self, html, name='video url', **kargs):
+ return self._html_search_regex([self._og_regex('video:secure_url'),
+ self._og_regex('video')],
+ html, name, **kargs)
+
class SearchInfoExtractor(InfoExtractor):
"""
Base class for paged search queries extractors.