midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[cspan] handle error massages and extract qualities

Browse source
This commit is contained in:
remitamine 2015-10-17 21:30:38 +01:00
parent 30787f7259
commit 355c7ad361
1 changed files with 41 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

67
youtube_dl/extractor/cspan.py
View file

@ -9,16 +9,21 @@ from ..utils import (
find_xpath_attr, find_xpath_attr,
smuggle_url, smuggle_url,
determine_ext, determine_ext,
ExtractorError,
) )
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'
_TESTS = [{ _TESTS = [{
'url': 'http://www.c-span.org/video/?313572-1/HolderonV', 'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
'md5': '067803f994e049b455a58b16e5aab442', 'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
'info_dict': { 'info_dict': {
'id': '315139', 'id': '315139',
'ext': 'mp4', 'ext': 'mp4',
@ -28,7 +33,7 @@ class CSpanIE(InfoExtractor):
'skip': 'Regularly fails on travis, for unknown reasons', 'skip': 'Regularly fails on travis, for unknown reasons',
}, { }, {
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
'md5': '4eafd1e91a75d2b1e6a3cbd0995816a2', 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
'info_dict': { 'info_dict': {
'id': 'c4486943', 'id': 'c4486943',
'ext': 'mp4', 'ext': 'mp4',
@ -37,7 +42,7 @@ class CSpanIE(InfoExtractor):
} }
}, { }, {
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
'md5': '446562a736c6bf97118e389433ed88d4', 'md5': '2ae5051559169baadba13fc35345ae74',
'info_dict': { 'info_dict': {
'id': '342759', 'id': '342759',
'ext': 'mp4', 'ext': 'mp4',
@ -71,8 +76,10 @@ class CSpanIE(InfoExtractor):
return self.url_result(surl, 'SenateISVP', video_id, title) return self.url_result(surl, 'SenateISVP', video_id, title)
data = self._download_json( data = self._download_json(
'http://c-spanvideo.org/videoLibrary/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_id)['video']
if data['@status'] != 'Success':
raise ExtractorError('%s said: %s' % (self.IE_NAME, 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),
@ -83,28 +90,36 @@ class CSpanIE(InfoExtractor):
title = find_xpath_attr(doc, './/string', 'name', 'title').text title = find_xpath_attr(doc, './/string', 'name', 'title').text
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
files = data['video']['files'] files = data['files']
try: capfile = get_text_attr(data, 'capfile')
capfile = data['video']['capfile']['#text']
except KeyError:
capfile = None
entries = [{ entries = []
'id': '%s_%d' % (video_id, partnum + 1), for partnum, f in enumerate(files):
'title': ( formats = []
title if len(files) == 1 else for quality in f['qualities']:
'%s part %d' % (title, partnum + 1)), formats.append({
'url': unescapeHTML(f['path']['#text']), 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
'description': description, 'url': unescapeHTML(get_text_attr(quality, 'file')),
'thumbnail': thumbnail, 'height': int_or_none(get_text_attr(quality, 'height')),
'duration': int_or_none(f.get('length', {}).get('#text')), 'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
'subtitles': { })
'en': [{ self._sort_formats(formats)
'url': capfile, entries.append({
'ext': determine_ext(capfile, 'dfxp') 'id': '%s_%d' % (video_id, partnum + 1),
}], 'title': (
} if capfile else None, title if len(files) == 1 else
} for partnum, f in enumerate(files)] '%s part %d' % (title, partnum + 1)),
'formats': formats,
'description': description,
'thumbnail': thumbnail,
'duration': int_or_none(get_text_attr(f, 'length')),
'subtitles': {
'en': [{
'url': capfile,
'ext': determine_ext(capfile, 'dfxp')
}],
} if capfile else None,
})
if len(entries) == 1: if len(entries) == 1:
entry = dict(entries[0]) entry = dict(entries[0])