[walla] Fix extractor and add subtitle tests

This commit is contained in:
Sergey M․ 2014-10-07 22:23:05 +07:00
parent c59c3c84ed
commit 7bc8780c57
2 changed files with 85 additions and 38 deletions

View File

@ -15,6 +15,7 @@
DailymotionIE, DailymotionIE,
TEDIE, TEDIE,
VimeoIE, VimeoIE,
WallaIE,
) )
@ -279,5 +280,32 @@ def test_multiple_langs(self):
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang) self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
class TestWallsSubtitles(BaseTestSubtitles):
url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
IE = WallaIE
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['heb']))
self.assertEqual(md5(subtitles['heb']), 'e758c5d7cb982f6bef14f377ec7a3920')
def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.url = 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

View File

@ -1,70 +1,89 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor
from ..utils import (
xpath_text,
int_or_none,
)
class WallaIE(InfoExtractor): class WallaIE(SubtitlesInfoExtractor):
_VALID_URL = r'http://vod\.walla\.co\.il/\w+/(?P<id>\d+)' _VALID_URL = r'http://vod\.walla\.co\.il/[^/]+/(?P<id>\d+)/(?P<display_id>.+)'
_TEST = { _TEST = {
'url': 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one', 'url': 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one',
'info_dict': { 'info_dict': {
'id': '2642630', 'id': '2642630',
'display_id': 'one-direction-all-for-one',
'ext': 'flv', 'ext': 'flv',
'title': 'וואן דיירקשן: ההיסטריה', 'title': 'וואן דיירקשן: ההיסטריה',
'description': 'md5:de9e2512a92442574cdb0913c49bc4d8',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 3600,
},
'params': {
# rtmp download
'skip_download': True,
} }
} }
_SUBTITLE_LANGS = {
'עברית': 'heb',
}
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')
display_id = mobj.group('display_id')
config_url = 'http://video2.walla.co.il/?w=null/null/%s/@@/video/flv_pl' % video_id video = self._download_xml(
'http://video2.walla.co.il/?w=null/null/%s/@@/video/flv_pl' % video_id,
display_id)
webpage = self._download_webpage(config_url, video_id, '') item = video.find('./items/item')
media_id = self._html_search_regex(r'<media_id>(\d+)</media_id>', webpage, video_id, 'extract media id') title = xpath_text(item, './title', 'title')
description = xpath_text(item, './synopsis', 'description')
prefix = '0' if len(media_id) == 7 else '' thumbnail = xpath_text(item, './preview_pic', 'thumbnail')
duration = int_or_none(xpath_text(item, './duration', 'duration'))
series = '%s%s' % (prefix, media_id[0:2])
session = media_id[2:5]
episode = media_id[5:7]
title = self._html_search_regex(r'<title>(.*)</title>', webpage, video_id, 'title')
default_quality = self._html_search_regex(r'<qualities defaultType="(\d+)">', webpage, video_id, 0)
quality = default_quality if default_quality else '40'
media_path = '/%s/%s/%s' % (series, session, media_id) #self._html_search_regex(r'<quality type="%s">.*<src>(.*)</src>' % default_quality ,webpage, '', flags=re.DOTALL)
playpath = 'mp4:media/%s/%s/%s-%s' % (series, session, media_id, quality) #self._html_search_regex(r'<quality type="%s">.*<src>(.*)</src>' % default_quality ,webpage, '', flags=re.DOTALL)
subtitles = {} subtitles = {}
for subtitle in item.findall('./subtitles/subtitle'):
lang = xpath_text(subtitle, './title')
subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = xpath_text(subtitle, './src')
subtitle_url = self._html_search_regex(r'<subtitles.*<src>(.*)</src>.*</subtitle>', webpage, video_id, 0) if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id, subtitles)
return
print subtitle_url subtitles = self.extract_subtitles(video_id, subtitles)
if subtitle_url: formats = []
subtitles_page = self._download_webpage(subtitle_url, video_id, '') for quality in item.findall('./qualities/quality'):
subtitles['heb'] = subtitles_page format_id = xpath_text(quality, './title')
fmt = {
'url': 'rtmp://wafla.walla.co.il/vod',
'play_path': xpath_text(quality, './src'),
'player_url': 'http://isc.walla.co.il/w9/swf/video_swf/vod/WallaMediaPlayerAvod.swf',
'page_url': url,
'ext': 'flv',
'format_id': xpath_text(quality, './title'),
}
m = re.search(r'^(?P<height>\d+)[Pp]', format_id)
if m:
fmt['height'] = int(m.group('height'))
formats.append(fmt)
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'title': title, 'title': title,
'url': 'rtmp://wafla.walla.co.il:1935/vod', 'description': description,
'player_url': 'http://isc.walla.co.il/w9/swf/video_swf/vod/WallaMediaPlayerAvod.swf', 'thumbnail': thumbnail,
'page_url': url, 'duration': duration,
'app': "vod", 'formats': formats,
'play_path': playpath,
'tc_url': 'rtmp://wafla.walla.co.il:1935/vod',
'rtmp_protocol': 'rtmp',
'ext': 'flv',
'subtitles': subtitles, 'subtitles': subtitles,
} }