+from __future__ import unicode_literals
+
import re
-import json
import itertools
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
- compat_urllib_request,
+ ExtractorError,
+ float_or_none,
+ int_or_none,
+ sanitized_Request,
+ urlencode_postdata,
)
class BambuserIE(InfoExtractor):
- IE_NAME = u'bambuser'
+ IE_NAME = 'bambuser'
_VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
_API_KEY = '005f64509e19a868399060af746a00aa'
+ _LOGIN_URL = 'https://bambuser.com/user'
+ _NETRC_MACHINE = 'bambuser'
_TEST = {
- u'url': u'http://bambuser.com/v/4050584',
+ 'url': 'http://bambuser.com/v/4050584',
# MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
- #u'md5': u'fba8f7693e48fd4e8641b3fd5539a641',
- u'info_dict': {
- u'id': u'4050584',
- u'ext': u'flv',
- u'title': u'Education engineering days - lightning talks',
- u'duration': 3741,
- u'uploader': u'pixelversity',
- u'uploader_id': u'344706',
+ # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
+ 'info_dict': {
+ 'id': '4050584',
+ 'ext': 'flv',
+ 'title': 'Education engineering days - lightning talks',
+ 'duration': 3741,
+ 'uploader': 'pixelversity',
+ 'uploader_id': '344706',
+ 'timestamp': 1382976692,
+ 'upload_date': '20131028',
+ 'view_count': int,
},
- u'params': {
+ 'params': {
# It doesn't respect the 'Range' header, it would download the whole video
# caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59
- u'skip_download': True,
+ 'skip_download': True,
},
}
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+
+ login_form = {
+ 'form_id': 'user_login',
+ 'op': 'Log in',
+ 'name': username,
+ 'pass': password,
+ }
+
+ request = sanitized_Request(
+ self._LOGIN_URL, urlencode_postdata(login_form))
+ request.add_header('Referer', self._LOGIN_URL)
+ response = self._download_webpage(
+ request, None, 'Logging in as %s' % username)
+
+ login_error = self._html_search_regex(
+ r'(?s)<div class="messages error">(.+?)</div>',
+ response, 'login error', default=None)
+ if login_error:
+ raise ExtractorError(
+ 'Unable to login: %s' % login_error, expected=True)
+
+ def _real_initialize(self):
+ self._login()
+
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- info_url = ('http://player-c.api.bambuser.com/getVideo.json?'
- '&api_key=%s&vid=%s' % (self._API_KEY, video_id))
- info_json = self._download_webpage(info_url, video_id)
- info = json.loads(info_json)['result']
+ video_id = self._match_id(url)
+
+ info = self._download_json(
+ 'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s'
+ % (self._API_KEY, video_id), video_id)
+
+ error = info.get('error')
+ if error:
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, error), expected=True)
+
+ result = info['result']
return {
'id': video_id,
- 'title': info['title'],
- 'url': info['url'],
- 'thumbnail': info.get('preview'),
- 'duration': int(info['length']),
- 'view_count': int(info['views_total']),
- 'uploader': info['username'],
- 'uploader_id': info['uid'],
+ 'title': result['title'],
+ 'url': result['url'],
+ 'thumbnail': result.get('preview'),
+ 'duration': int_or_none(result.get('length')),
+ 'uploader': result.get('username'),
+ 'uploader_id': compat_str(result.get('owner', {}).get('uid')),
+ 'timestamp': int_or_none(result.get('created')),
+ 'fps': float_or_none(result.get('framerate')),
+ 'view_count': int_or_none(result.get('views_total')),
+ 'comment_count': int_or_none(result.get('comment_count')),
}
class BambuserChannelIE(InfoExtractor):
- IE_NAME = u'bambuser:channel'
- _VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
+ IE_NAME = 'bambuser:channel'
+ _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
# The maximum number we can get with each request
_STEP = 50
+ _TEST = {
+ 'url': 'http://bambuser.com/channel/pixelversity',
+ 'info_dict': {
+ 'title': 'pixelversity',
+ },
+ 'playlist_mincount': 60,
+ }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
urls = []
last_id = ''
for i in itertools.count(1):
- req_url = ('http://bambuser.com/xhr-api/index.php?username={user}'
+ req_url = (
+ 'http://bambuser.com/xhr-api/index.php?username={user}'
'&sort=created&access_mode=0%2C1%2C2&limit={count}'
'&method=broadcast&format=json&vid_older_than={last}'
- ).format(user=user, count=self._STEP, last=last_id)
- req = compat_urllib_request.Request(req_url)
+ ).format(user=user, count=self._STEP, last=last_id)
+ req = sanitized_Request(req_url)
# Without setting this header, we wouldn't get any result
req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
- info_json = self._download_webpage(req, user,
- u'Downloading page %d' % i)
- results = json.loads(info_json)['result']
- if len(results) == 0:
+ data = self._download_json(
+ req, user, 'Downloading page %d' % i)
+ results = data['result']
+ if not results:
break
last_id = results[-1]['vid']
urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)
Rapsys Git / youtubedl / blobdiff