[googledrive] Simplify and carry long lines (#13638)

This commit is contained in:
Sergey M․ 2017-08-23 00:33:53 +07:00
parent e01c3d2ef7
commit 37d9af306a
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -7,7 +7,6 @@
ExtractorError, ExtractorError,
int_or_none, int_or_none,
lowercase_escape, lowercase_escape,
error_to_compat_str,
update_url_query, update_url_query,
) )
@ -59,7 +58,7 @@ class GoogleDriveIE(InfoExtractor):
'automatic_captions': 'target', 'automatic_captions': 'target',
} }
_caption_formats_ext = [] _caption_formats_ext = []
_captions_by_country_xml = None _captions_xml = None
@staticmethod @staticmethod
def _extract_url(webpage): def _extract_url(webpage):
@ -69,96 +68,99 @@ def _extract_url(webpage):
if mobj: if mobj:
return 'https://drive.google.com/file/d/%s' % mobj.group('id') return 'https://drive.google.com/file/d/%s' % mobj.group('id')
def _set_captions_data(self, video_id, video_subtitles_id, hl): def _download_subtitles_xml(self, video_id, subtitles_id, hl):
try: if self._captions_xml:
self._captions_by_country_xml = self._download_xml(self._BASE_URL_CAPTIONS, video_id, query={ return
self._captions_xml = self._download_xml(
self._BASE_URL_CAPTIONS, video_id, query={
'id': video_id, 'id': video_id,
'vid': video_subtitles_id, 'vid': subtitles_id,
'hl': hl, 'hl': hl,
'v': video_id, 'v': video_id,
'type': 'list', 'type': 'list',
'tlangs': '1', 'tlangs': '1',
'fmts': '1', 'fmts': '1',
'vssids': '1', 'vssids': '1',
}) }, note='Downloading subtitles XML',
except ExtractorError as ee: errnote='Unable to download subtitles XML', fatal=False)
self.report_warning('unable to download video subtitles: %s' % error_to_compat_str(ee)) if self._captions_xml:
if self._captions_by_country_xml is not None: for f in self._captions_xml.findall('format'):
caption_available_extensions = self._captions_by_country_xml.findall('format') if f.attrib.get('fmt_code') and not f.attrib.get('default'):
for caption_extension in caption_available_extensions: self._caption_formats_ext.append(f.attrib['fmt_code'])
if caption_extension.attrib.get('fmt_code') and not caption_extension.attrib.get('default'):
self._caption_formats_ext.append(caption_extension.attrib['fmt_code'])
def _get_captions_by_type(self, video_id, video_subtitles_id, caption_type, caption_original_lang_code=None): def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
if not video_subtitles_id or not caption_type: origin_lang_code=None):
return None if not subtitles_id or not caption_type:
return
captions = {} captions = {}
for caption_entry in self._captions_by_country_xml.findall(self._CAPTIONS_ENTRY_TAG[caption_type]): for caption_entry in self._captions_xml.findall(
self._CAPTIONS_ENTRY_TAG[caption_type]):
caption_lang_code = caption_entry.attrib.get('lang_code') caption_lang_code = caption_entry.attrib.get('lang_code')
if not caption_lang_code: if not caption_lang_code:
continue continue
caption_format_data = [] caption_format_data = []
for caption_format in self._caption_formats_ext: for caption_format in self._caption_formats_ext:
query = { query = {
'vid': video_subtitles_id, 'vid': subtitles_id,
'v': video_id, 'v': video_id,
'fmt': caption_format, 'fmt': caption_format,
'lang': caption_lang_code if caption_original_lang_code is None else caption_original_lang_code, 'lang': (caption_lang_code if origin_lang_code is None
else origin_lang_code),
'type': 'track', 'type': 'track',
'name': '', 'name': '',
'kind': '', 'kind': '',
} }
if caption_original_lang_code is not None: if origin_lang_code is not None:
query.update({'tlang': caption_lang_code}) query.update({'tlang': caption_lang_code})
caption_format_data.append({ caption_format_data.append({
'url': update_url_query(self._BASE_URL_CAPTIONS, query), 'url': update_url_query(self._BASE_URL_CAPTIONS, query),
'ext': caption_format, 'ext': caption_format,
}) })
captions[caption_lang_code] = caption_format_data captions[caption_lang_code] = caption_format_data
if not captions:
self.report_warning('video doesn\'t have %s' % caption_type.replace('_', ' '))
return captions return captions
def _get_subtitles(self, video_id, video_subtitles_id, hl): def _get_subtitles(self, video_id, subtitles_id, hl):
if not video_subtitles_id or not hl: if not subtitles_id or not hl:
return None return
if self._captions_by_country_xml is None: self._download_subtitles_xml(video_id, subtitles_id, hl)
self._set_captions_data(video_id, video_subtitles_id, hl) if not self._captions_xml:
if self._captions_by_country_xml is None: return
return None return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
return self._get_captions_by_type(video_id, video_subtitles_id, 'subtitles')
def _get_automatic_captions(self, video_id, video_subtitles_id, hl): def _get_automatic_captions(self, video_id, subtitles_id, hl):
if not video_subtitles_id or not hl: if not subtitles_id or not hl:
return None return
if self._captions_by_country_xml is None: self._download_subtitles_xml(video_id, subtitles_id, hl)
self._set_captions_data(video_id, video_subtitles_id, hl) if not self._captions_xml:
if self._captions_by_country_xml is None: return
return None track = self._captions_xml.find('track')
self.to_screen('%s: Looking for automatic captions' % video_id) if track is None:
subtitle_original_track = self._captions_by_country_xml.find('track') return
if subtitle_original_track is None: origin_lang_code = track.attrib.get('lang_code')
return None if not origin_lang_code:
subtitle_original_lang_code = subtitle_original_track.attrib.get('lang_code') return
if not subtitle_original_lang_code: return self._get_captions_by_type(
return None video_id, subtitles_id, 'automatic_captions', origin_lang_code)
return self._get_captions_by_type(video_id, video_subtitles_id, 'automatic_captions', subtitle_original_lang_code)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage( webpage = self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id) 'http://docs.google.com/file/d/%s' % video_id, video_id)
reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None) reason = self._search_regex(
r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason: if reason:
raise ExtractorError(reason) raise ExtractorError(reason)
title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title') title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
duration = int_or_none(self._search_regex( duration = int_or_none(self._search_regex(
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None)) r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
default=None))
fmt_stream_map = self._search_regex( fmt_stream_map = self._search_regex(
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',') r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',') 'fmt stream map').split(',')
fmt_list = self._search_regex(
r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
resolutions = {} resolutions = {}
for fmt in fmt_list: for fmt in fmt_list:
@ -190,12 +192,14 @@ def _real_extract(self, url):
hl = self._search_regex( hl = self._search_regex(
r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None) r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
video_subtitles_id = None subtitles_id = None
ttsurl = self._search_regex( ttsurl = self._search_regex(
r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None) r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
if ttsurl: if ttsurl:
# the video Id for subtitles will be the last value in the ttsurl query string # the video Id for subtitles will be the last value in the ttsurl
video_subtitles_id = ttsurl.encode('utf-8').decode('unicode_escape').split('=')[-1] # query string
subtitles_id = ttsurl.encode('utf-8').decode(
'unicode_escape').split('=')[-1]
return { return {
'id': video_id, 'id': video_id,
@ -203,6 +207,7 @@ def _real_extract(self, url):
'thumbnail': self._og_search_thumbnail(webpage, default=None), 'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
'subtitles': self.extract_subtitles(video_id, video_subtitles_id, hl), 'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
'automatic_captions': self.extract_automatic_captions(video_id, video_subtitles_id, hl), 'automatic_captions': self.extract_automatic_captions(
video_id, subtitles_id, hl),
} }