Browse Source

[toypics] Separate user and video extraction (#2601)

totalwebcasting
Philipp Hagemeister 11 years ago
parent
commit
231f76b530
3 changed files with 59 additions and 29 deletions
  1. +9
    -0
      test/test_playlists.py
  2. +1
    -1
      youtube_dl/extractor/__init__.py
  3. +49
    -28
      youtube_dl/extractor/toypics.py

+ 9
- 0
test/test_playlists.py View File

@ -37,6 +37,7 @@ from youtube_dl.extractor import (
GoogleSearchIE,
GenericIE,
TEDIE,
ToypicsUserIE,
)
@ -269,5 +270,13 @@ class TestPlaylists(unittest.TestCase):
self.assertEqual(result['title'], 'Who are the hackers?')
self.assertTrue(len(result['entries']) >= 6)
def test_toypics_user(self):
dl = FakeYDL()
ie = ToypicsUserIE(dl)
result = ie.extract('http://videos.toypics.net/Mikey')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'Mikey')
self.assertTrue(len(result['entries']) >= 17)
if __name__ == '__main__':
unittest.main()

+ 1
- 1
youtube_dl/extractor/__init__.py View File

@ -239,7 +239,7 @@ from .theplatform import ThePlatformIE
from .thisav import ThisAVIE
from .tinypic import TinyPicIE
from .toutv import TouTvIE
from .toypics import ToypicsIE
from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .trutube import TruTubeIE


+ 49
- 28
youtube_dl/extractor/toypics.py View File

@ -2,43 +2,26 @@ from .common import InfoExtractor
from math import ceil
import re
class ToypicsIE(InfoExtractor):
_VALID_URL = r'(?:http://)?videos\.toypics\.net/.*'
IE_DESC = 'Toypics user profile'
_VALID_URL = r'http://videos\.toypics\.net/view/(?P<id>[0-9]+)/.*'
_TEST = {
'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/',
#'md5': '8a8b546956bbd0e769dbe28f6e80abb3', == $head -c10K 12929646011616163504.mp4 |md5sum //no idea why it fails
'md5': '16e806ad6d6f58079d210fe30985e08b',
'info_dict': {
'id': '514',
'ext': 'mp4',
'title': 'Chance-Bulge\'d, 2',
'age_limit': 18
'age_limit': 18,
'uploader': 'kidsune',
}
}
PAGINATED=8
def _real_extract(self, url):
mobj = re.match(r'(http://)?videos\.toypics\.net/(?P<username>[^/?]+)$', url)
if not mobj:
return self.extract_one(url)
return [self.extract_one(u) for u in self.process_paginated(url,
r'public/">Public Videos \((?P<videos_count>[0-9]+)\)</a></li>',
r'<p class="video-entry-title">\n\s*<a href="(http://videos.toypics.net/view/[^"]+)">'
)]
def process_paginated(self, profile_url, re_total, re_video_page):
profile_page = self._download_webpage(profile_url, 'profile' , 'getting profile page: '+profile_url)
videos_count = self._html_search_regex(re_total, profile_page, 'videos count')
lst = []
for n in xrange(1,int(ceil(float(videos_count)/self.PAGINATED)) +1):
lpage_url = profile_url +'/public/%d'%n
lpage = self._download_webpage(lpage_url, 'page %d'%n)
lst.extend(re.findall(re_video_page, lpage))
return lst
def extract_one(self,url):
mobj = re.match(r'(http://)?videos\.toypics\.net/view/(?P<videoid>[0-9]+)/.*', url)
video_id = mobj.group('videoid')
page = self._download_webpage(url, video_id, 'getting page: '+url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'src:\s+"(http://static[0-9]+\.toypics\.net/flvideo/[^"]+)"', page, 'video URL')
title = self._html_search_regex(
@ -48,8 +31,46 @@ class ToypicsIE(InfoExtractor):
return {
'id': video_id,
'url': video_url,
'ext': video_url[-3:],
'title': title,
'uploader': username,
'age_limit': 18
'age_limit': 18,
}
class ToypicsUserIE(InfoExtractor):
IE_DESC = 'Toypics user profile'
_VALID_URL = r'http://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
username = mobj.group('username')
profile_page = self._download_webpage(
url, username, note='Retrieving profile page')
video_count = int(self._search_regex(
r'public/">Public Videos \(([0-9]+)\)</a></li>', profile_page,
'video count'))
PAGE_SIZE = 8
urls = []
page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE
for n in range(1, page_count + 1):
lpage_url = url + '/public/%d' % n
lpage = self._download_webpage(
lpage_url, username,
note='Downloading page %d/%d' % (n, page_count))
urls.extend(
re.findall(
r'<p class="video-entry-title">\n\s*<a href="(http://videos.toypics.net/view/[^"]+)">',
lpage))
return {
'_type': 'playlist',
'id': username,
'entries': [{
'_type': 'url',
'url': url,
'ie_key': 'Toypics',
} for url in urls]
}

Loading…
Cancel
Save