[tvp:series] Fix extraction

pull/2/head
Sergey M․ 6 years ago
parent 34568dc296
commit d93083789b
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

@ -1,14 +1,16 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import itertools
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext,
clean_html, clean_html,
get_element_by_attribute, determine_ext,
ExtractorError, ExtractorError,
get_element_by_attribute,
orderedSet,
) )
@ -198,46 +200,35 @@ class TVPEmbedIE(InfoExtractor):
class TVPSeriesIE(InfoExtractor): class TVPSeriesIE(InfoExtractor):
IE_NAME = 'tvp:series' IE_NAME = 'tvp:series'
_VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$' _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)/video'
_TESTS = [{ _TESTS = [{
'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem', 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video',
'info_dict': { 'info_dict': {
'title': 'Ogniem i mieczem', 'id': '38678312',
'id': '4278026',
}, },
'playlist_count': 4, 'playlist_count': 115,
}, {
'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat',
'info_dict': {
'title': 'Boso przez świat',
'id': '9329207',
},
'playlist_count': 86,
}] }]
def _real_extract(self, url): def _entries(self, url, display_id):
display_id = self._match_id(url) for page_num in itertools.count(1):
webpage = self._download_webpage(url, display_id, tries=5) page = self._download_webpage(
url, display_id, 'Downloading page %d' % page_num,
title = self._html_search_regex( query={'page': page_num})
r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series')
playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id')
playlist = self._download_webpage(
'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend'
'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5,
note='Downloading playlist')
videos_paths = re.findall(
'(?s)class="shortTitle">.*?href="(/[^"]+)', playlist)
entries = [
self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key())
for v_path in videos_paths]
return { video_ids = orderedSet(re.findall(
'_type': 'playlist', r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id,
'id': playlist_id, page))
'display_id': display_id,
'title': title, if not video_ids:
'entries': entries, break
}
for video_id in video_ids:
yield self.url_result(
'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(),
video_id=video_id)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id, playlist_id = mobj.group('display_id', 'id')
return self.playlist_result(self._entries(url, display_id), playlist_id)

Loading…
Cancel
Save