mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-12-22 16:57:40 +00:00
[camdemy] Add new extractor
Single file download done, while folder extaction in plan
This commit is contained in:
parent
054fe3cc40
commit
8708d76425
2 changed files with 79 additions and 0 deletions
|
@ -49,6 +49,7 @@ from .brightcove import BrightcoveIE
|
|||
from .buzzfeed import BuzzFeedIE
|
||||
from .byutv import BYUtvIE
|
||||
from .c56 import C56IE
|
||||
from .camdemy import CamdemyIE
|
||||
from .canal13cl import Canal13clIE
|
||||
from .canalplus import CanalplusIE
|
||||
from .canalc2 import Canalc2IE
|
||||
|
|
78
youtube_dl/extractor/camdemy.py
Normal file
78
youtube_dl/extractor/camdemy.py
Normal file
|
@ -0,0 +1,78 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import parse_iso8601
|
||||
|
||||
|
||||
class CamdemyIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www.camdemy.com/media/(?P<id>\d+).*'
|
||||
_TESTS = [{
|
||||
# single file
|
||||
'url': 'http://www.camdemy.com/media/5181/',
|
||||
'md5': '5a5562b6a98b37873119102e052e311b',
|
||||
'info_dict': {
|
||||
'id': '5181',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'description': '',
|
||||
'creator': 'ss11spring',
|
||||
'upload_date': '20130114',
|
||||
'timestamp': 1358154556,
|
||||
}
|
||||
}, {
|
||||
# With non-empty description
|
||||
'url': 'http://www.camdemy.com/media/13885',
|
||||
'md5': '4576a3bb2581f86c61044822adbd1249',
|
||||
'info_dict': {
|
||||
'id': '13885',
|
||||
'ext': 'mp4',
|
||||
'title': 'EverCam + Camdemy QuickStart',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
|
||||
'creator': 'evercam',
|
||||
'upload_date': '20140620',
|
||||
'timestamp': 1403271569,
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
page = self._download_webpage(url, video_id)
|
||||
|
||||
oembed_obj = self._download_json(
|
||||
'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
|
||||
|
||||
thumb_url = oembed_obj['thumbnail_url']
|
||||
video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
|
||||
fileListXML = self._download_xml(
|
||||
compat_urlparse.urljoin(video_folder, 'fileList.xml'),
|
||||
video_id, 'Filelist XML')
|
||||
fileName = fileListXML.find('./video/item/fileName').text
|
||||
|
||||
creation_time = self._html_search_regex(
|
||||
r"<div class='title'>Posted :</div>.*<div class='value'>([0-9:\- ]+)<",
|
||||
page, 'creation time', flags=re.MULTILINE | re.DOTALL) + '+08:00'
|
||||
creation_timestamp = parse_iso8601(creation_time, delimiter=' ')
|
||||
|
||||
view_count_str = self._html_search_regex(
|
||||
r"<div class='title'>Views :</div>.*<div class='value'>([0-9,]+)<",
|
||||
page, 'view count', flags=re.MULTILINE | re.DOTALL)
|
||||
views = int(view_count_str.replace(',', ''))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': compat_urlparse.urljoin(video_folder, fileName),
|
||||
'title': oembed_obj['title'],
|
||||
'thumbnail': thumb_url,
|
||||
'description': self._html_search_meta('description', page),
|
||||
'creator': oembed_obj['author_name'],
|
||||
'duration': oembed_obj['duration'],
|
||||
'timestamp': creation_timestamp,
|
||||
'view_count': views,
|
||||
}
|
Loading…
Reference in a new issue