[orf:tvthek] Fix extraction and modernize (closes #10898)

This commit is contained in:
Sergey M․ 2016-10-14 23:43:09 +07:00
parent dff5107b68
commit 73c801d660
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 23 additions and 23 deletions

View File

@ -1,28 +1,28 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re import re
import calendar import calendar
import datetime import datetime
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import ( from ..utils import (
HEADRequest, HEADRequest,
unified_strdate, unified_strdate,
ExtractorError,
strip_jsonp, strip_jsonp,
int_or_none, int_or_none,
float_or_none, float_or_none,
determine_ext, determine_ext,
remove_end, remove_end,
unescapeHTML,
) )
class ORFTVthekIE(InfoExtractor): class ORFTVthekIE(InfoExtractor):
IE_NAME = 'orf:tvthek' IE_NAME = 'orf:tvthek'
IE_DESC = 'ORF TVthek' IE_DESC = 'ORF TVthek'
_VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics?/.+?|program/[^/]+)/(?P<id>\d+)' _VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389', 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
@ -51,26 +51,23 @@ class ORFTVthekIE(InfoExtractor):
'skip_download': True, # rtsp downloads 'skip_download': True, # rtsp downloads
}, },
'_skip': 'Blocked outside of Austria / Germany', '_skip': 'Blocked outside of Austria / Germany',
}, {
'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
'skip_download': True,
}, {
'url': 'http://tvthek.orf.at/profile/Universum/35429',
'skip_download': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id) webpage = self._download_webpage(url, playlist_id)
data_json = self._search_regex( data_jsb = self._parse_json(
r'initializeAdworx\((.+?)\);\n', webpage, 'video info') self._search_regex(
all_data = json.loads(data_json) r'<div[^>]+class=(["\']).*?VideoPlaylist.*?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
webpage, 'playlist', group='json'),
def get_segments(all_data): playlist_id, transform_source=unescapeHTML)['playlist']['videos']
for data in all_data:
if data['name'] in (
'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM',
'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'):
return data['values']['segments']
sdata = get_segments(all_data)
if not sdata:
raise ExtractorError('Unable to extract segments')
def quality_to_int(s): def quality_to_int(s):
m = re.search('([0-9]+)', s) m = re.search('([0-9]+)', s)
@ -79,8 +76,11 @@ class ORFTVthekIE(InfoExtractor):
return int(m.group(1)) return int(m.group(1))
entries = [] entries = []
for sd in sdata: for sd in data_jsb:
video_id = sd['id'] video_id, title = sd.get('id'), sd.get('title')
if not video_id or not title:
continue
video_id = compat_str(video_id)
formats = [{ formats = [{
'preference': -10 if fd['delivery'] == 'hls' else None, 'preference': -10 if fd['delivery'] == 'hls' else None,
'format_id': '%s-%s-%s' % ( 'format_id': '%s-%s-%s' % (
@ -88,7 +88,7 @@ class ORFTVthekIE(InfoExtractor):
'url': fd['src'], 'url': fd['src'],
'protocol': fd['protocol'], 'protocol': fd['protocol'],
'quality': quality_to_int(fd['quality']), 'quality': quality_to_int(fd['quality']),
} for fd in sd['playlist_item_array']['sources']] } for fd in sd['sources']]
# Check for geoblocking. # Check for geoblocking.
# There is a property is_geoprotection, but that's always false # There is a property is_geoprotection, but that's always false
@ -115,14 +115,14 @@ class ORFTVthekIE(InfoExtractor):
self._check_formats(formats, video_id) self._check_formats(formats, video_id)
self._sort_formats(formats) self._sort_formats(formats)
upload_date = unified_strdate(sd['created_date']) upload_date = unified_strdate(sd.get('created_date'))
entries.append({ entries.append({
'_type': 'video', '_type': 'video',
'id': video_id, 'id': video_id,
'title': sd['header'], 'title': title,
'formats': formats, 'formats': formats,
'description': sd.get('description'), 'description': sd.get('description'),
'duration': int(sd['duration_in_seconds']), 'duration': int_or_none(sd.get('duration_in_seconds')),
'upload_date': upload_date, 'upload_date': upload_date,
'thumbnail': sd.get('image_full_url'), 'thumbnail': sd.get('image_full_url'),
}) })