[dailymotion] Add an extractor for Dailymotion playlists

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-07-29 12:07:38 +02:00
parent 58261235f0
commit a3c736def2
3 changed files with 62 additions and 1 deletions

30
test/test_playlists.py Normal file
View File

@ -0,0 +1,30 @@
#!/usr/bin/env python
import sys
import unittest
import json
# Allow direct execution
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import DailymotionPlaylistIE
from youtube_dl.utils import *
from helper import FakeYDL
class TestPlaylists(unittest.TestCase):
def assertIsPlaylist(self, info):
"""Make sure the info has '_type' set to 'playlist'"""
self.assertEqual(info['_type'], 'playlist')
def test_dailymotion_playlist(self):
dl = FakeYDL()
ie = DailymotionPlaylistIE(dl)
result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'SPORT')
self.assertTrue(len(result['entries']) > 20)
if __name__ == '__main__':
unittest.main()

View File

@ -12,7 +12,7 @@
from .condenast import CondeNastIE
from .criterion import CriterionIE
from .cspan import CSpanIE
from .dailymotion import DailymotionIE
from .dailymotion import DailymotionIE, DailymotionPlaylistIE
from .depositfiles import DepositFilesIE
from .dotsub import DotsubIE
from .dreisat import DreiSatIE

View File

@ -1,9 +1,12 @@
import re
import json
import itertools
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
get_element_by_attribute,
get_element_by_id,
ExtractorError,
)
@ -77,3 +80,31 @@ def _real_extract(self, url):
'ext': video_extension,
'thumbnail': info['thumbnail_url']
}]
class DailymotionPlaylistIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
_MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
video_ids = []
for pagenum in itertools.count(1):
webpage = self._download_webpage('https://www.dailymotion.com/playlist/%s/%s' % (playlist_id, pagenum),
playlist_id, u'Downloading page %s' % pagenum)
playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
entries = [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
for video_id in video_ids]
return {'_type': 'playlist',
'id': playlist_id,
'title': get_element_by_id(u'playlist_name', webpage),
'entries': entries,
}