github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-26 02:02:19 +00:00
Code Issues Projects Releases Packages Wiki Activity

[cspan] move get_text_attr to CSpanIE

Browse source
This commit is contained in:
remitamine 2015-10-20 07:43:39 +01:00
parent 355c7ad361
commit 4bf5614195
1 changed files with 10 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
youtube_dl/extractor/cspan.py
View file

@ -14,10 +14,6 @@
from .senateisvp import SenateISVPIE from .senateisvp import SenateISVPIE
def get_text_attr(d, attr):
return d.get(attr, {}).get('#text')
class CSpanIE(InfoExtractor): class CSpanIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)' _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
IE_DESC = 'C-SPAN' IE_DESC = 'C-SPAN'
@ -60,6 +56,9 @@ class CSpanIE(InfoExtractor):
} }
}] }]
def get_text_attr(self, d, attr):
return d.get(attr, {}).get('#text')
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(url, video_id) webpage = self._download_webpage(url, video_id)
@ -79,7 +78,7 @@ def _real_extract(self, url):
'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id), 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
video_id)['video'] video_id)['video']
if data['@status'] != 'Success': if data['@status'] != 'Success':
raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True) raise ExtractorError('%s said: %s' % (self.IE_NAME, self.get_text_attr(data, 'error')), expected=True)
doc = self._download_xml( doc = self._download_xml(
'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id), 'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
@ -91,17 +90,17 @@ def _real_extract(self, url):
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
files = data['files'] files = data['files']
capfile = get_text_attr(data, 'capfile') capfile = self.get_text_attr(data, 'capfile')
entries = [] entries = []
for partnum, f in enumerate(files): for partnum, f in enumerate(files):
formats = [] formats = []
for quality in f['qualities']: for quality in f['qualities']:
formats.append({ formats.append({
'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')), 'format_id': '%s-%sp' % (self.get_text_attr(quality, 'bitrate'), self.get_text_attr(quality, 'height')),
'url': unescapeHTML(get_text_attr(quality, 'file')), 'url': unescapeHTML(self.get_text_attr(quality, 'file')),
'height': int_or_none(get_text_attr(quality, 'height')), 'height': int_or_none(self.get_text_attr(quality, 'height')),
'tbr': int_or_none(get_text_attr(quality, 'bitrate')), 'tbr': int_or_none(self.get_text_attr(quality, 'bitrate')),
}) })
self._sort_formats(formats) self._sort_formats(formats)
entries.append({ entries.append({
@ -112,7 +111,7 @@ def _real_extract(self, url):
'formats': formats, 'formats': formats,
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': int_or_none(get_text_attr(f, 'length')), 'duration': int_or_none(self.get_text_attr(f, 'length')),
'subtitles': { 'subtitles': {
'en': [{ 'en': [{
'url': capfile, 'url': capfile,