mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 02:42:30 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

BBCNewsIE: eliminate redundant function.

Browse Source 
BBCCoUkIE._download_media_selector: use class variable instead of
hardcoded string for mediaselector_url template.
This commit is contained in:
fnord 2015-06-19 01:52:25 -05:00
parent 9e96dc8b35
commit a8b081a052
2 changed files with 5 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
youtube_dl/extractor/bbccouk.py
View File

@ -15,6 +15,8 @@ class BBCCoUkIE(InfoExtractor):
IE_DESC = 'BBC iPlayer' IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})' _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'
_TESTS = [ _TESTS = [
{ {
'url': 'http://www.bbc.co.uk/programmes/b039g8p7', 'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
@ -277,7 +279,7 @@ def _extract_text(p):
def _download_media_selector(self, programme_id): def _download_media_selector(self, programme_id):
try: try:
media_selection = self._download_xml( media_selection = self._download_xml(
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, self.mediaselector_url % programme_id,
programme_id, 'Downloading media selection XML') programme_id, 'Downloading media selection XML')
except ExtractorError as ee: except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:

42
youtube_dl/extractor/bbcnews.py
View File

@ -14,6 +14,8 @@ class BBCNewsIE(BBCCoUkIE):
IE_DESC = 'BBC news' IE_DESC = 'BBC news'
_VALID_URL = r'https?://(?:www\.)?(?:bbc\.co\.uk|bbc\.com)/news/(?P<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?(?:bbc\.co\.uk|bbc\.com)/news/(?P<id>[^/]+)'
mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s'
_TESTS = [{ _TESTS = [{
'url': 'http://www.bbc.com/news/world-europe-32668511', 'url': 'http://www.bbc.com/news/world-europe-32668511',
'info_dict': { 'info_dict': {
@ -59,46 +61,6 @@ def _duration_str2int(self, str):
return total return total
return None return None
def _download_media_selector(self, programme_id):
# bbc news uses http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/ not
# http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/
# Could add third urlspec arg to BBCCoUkIE._download_media_selector instead of duplicating it
try:
media_selection = self._download_xml(
'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s' % programme_id,
programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
else:
raise
formats = []
subtitles = None
for media in self._extract_medias(media_selection):
kind = media.get('kind')
if kind == 'audio':
formats.extend(self._extract_audio(media, programme_id))
elif kind == 'video':
formats.extend(self._extract_video(media, programme_id))
elif kind == 'captions':
subtitles = self.extract_subtitles(media, programme_id)
formats = []
subtitles = None
for media in self._extract_medias(media_selection):
kind = media.get('kind')
if kind == 'audio':
formats.extend(self._extract_audio(media, programme_id))
elif kind == 'video':
formats.extend(self._extract_video(media, programme_id))
elif kind == 'captions':
subtitles = self.extract_subtitles(media, programme_id)
return formats, subtitles
def _real_extract(self, url): def _real_extract(self, url):
list_id = self._match_id(url) list_id = self._match_id(url)
webpage = self._download_webpage(url, list_id) webpage = self._download_webpage(url, list_id)