[tvp] Minor improvements (#1730)

This commit is contained in:
Philipp Hagemeister 2013-11-13 11:06:53 +01:00
parent 6c5ad80cdc
commit c3a3028f9f

View file

@ -1,23 +1,17 @@
# encoding: utf-8
import re
import json import json
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
RegexNotFoundError,
)
class TvpIE(InfoExtractor): class TvpIE(InfoExtractor):
IE_NAME = u'tvp.pl' IE_NAME = u'tvp.pl'
_VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)' _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)'
_INFO_URL = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s'
_TEST = { _TEST = {
u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
u'file': u'31.10.2013-12878238.wmv', u'md5': u'148408967a6a468953c0a75cbdaf0d7a',
u'file': u'12878238.wmv',
u'info_dict': { u'info_dict': {
u'title': u'31.10.2013', u'title': u'31.10.2013',
u'description': u'31.10.2013', u'description': u'31.10.2013',
@ -27,34 +21,21 @@ class TvpIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id, "Downloading video webpage") webpage = self._download_webpage(url, video_id)
json_params = self._download_webpage(self._INFO_URL % video_id, video_id, "Downloading video metadata") json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id
json_params = self._download_webpage(
json_url, video_id, u"Downloading video metadata")
try:
params = json.loads(json_params) params = json.loads(json_params)
except:
raise ExtractorError(u'Invalid JSON')
self.report_extraction(video_id) self.report_extraction(video_id)
try:
video_url = params['video_url'] video_url = params['video_url']
except KeyError:
raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
try: title = self._og_search_title(webpage, fatal=True)
title = self._og_search_title(webpage) return {
except RegexNotFoundError:
title = video_id
info = {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'ext': 'wmv', 'ext': 'wmv',
'url': video_url, 'url': video_url,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
} }
try:
info['description'] = self._og_search_description(webpage)
info['thumbnail'] = self._og_search_thumbnail(webpage)
except RegexNotFoundError:
pass
return info