yt-dlp/youtube_dlc/extractor/camdemy.py

162 lines
5.6 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
2016-07-25 17:31:10 +02:00
clean_html,
2016-07-25 17:35:12 +02:00
parse_duration,
str_to_int,
2016-07-25 17:31:10 +02:00
unified_strdate,
)
class CamdemyIE(InfoExtractor):
_VALID_URL = r'https?://(?: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': r're:^https?://.*\.jpg$',
'creator': 'ss11spring',
2016-07-25 17:35:12 +02:00
'duration': 1591,
'upload_date': '20130114',
'view_count': int,
}
}, {
# With non-empty description
2016-07-25 17:31:10 +02:00
# webpage returns "No permission or not login"
'url': 'http://www.camdemy.com/media/13885',
'md5': '4576a3bb2581f86c61044822adbd1249',
'info_dict': {
'id': '13885',
'ext': 'mp4',
'title': 'EverCam + Camdemy QuickStart',
'thumbnail': r're:^https?://.*\.jpg$',
2016-07-25 17:31:10 +02:00
'description': 'md5:2a9f989c2b153a2342acee579c6e7db6',
'creator': 'evercam',
2016-07-25 17:35:12 +02:00
'duration': 318,
}
}, {
2016-07-25 17:31:10 +02:00
# External source (YouTube)
'url': 'http://www.camdemy.com/media/14842',
'info_dict': {
'id': '2vsYQzNIsJo',
'ext': 'mp4',
2016-07-25 17:31:10 +02:00
'title': 'Excel 2013 Tutorial - How to add Password Protection',
'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
'upload_date': '20130211',
'uploader': 'Hun Kim',
'uploader_id': 'hunkimtutorials',
2016-07-25 17:31:10 +02:00
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
2016-07-25 17:31:10 +02:00
webpage = self._download_webpage(url, video_id)
src_from = self._html_search_regex(
2016-07-25 17:31:10 +02:00
r"class=['\"]srcFrom['\"][^>]*>Sources?(?:\s+from)?\s*:\s*<a[^>]+(?:href|title)=(['\"])(?P<url>(?:(?!\1).)+)\1",
webpage, 'external source', default=None, group='url')
if src_from:
return self.url_result(src_from)
oembed_obj = self._download_json(
'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
2016-07-25 17:35:12 +02:00
title = oembed_obj['title']
thumb_url = oembed_obj['thumbnail_url']
2015-02-12 07:23:25 +01:00
video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
file_list_doc = self._download_xml(
2015-02-12 07:23:25 +01:00
compat_urlparse.urljoin(video_folder, 'fileList.xml'),
2016-07-25 17:31:10 +02:00
video_id, 'Downloading filelist XML')
file_name = file_list_doc.find('./video/item/fileName').text
video_url = compat_urlparse.urljoin(video_folder, file_name)
2016-07-25 17:31:10 +02:00
# Some URLs return "No permission or not login" in a webpage despite being
# freely available via oembed JSON URL (e.g. http://www.camdemy.com/media/13885)
upload_date = unified_strdate(self._search_regex(
r'>published on ([^<]+)<', webpage,
'upload date', default=None))
view_count = str_to_int(self._search_regex(
r'role=["\']viewCnt["\'][^>]*>([\d,.]+) views',
webpage, 'view count', default=None))
description = self._html_search_meta(
'description', webpage, default=None) or clean_html(
oembed_obj.get('description'))
return {
'id': video_id,
'url': video_url,
2016-07-25 17:35:12 +02:00
'title': title,
'thumbnail': thumb_url,
2016-07-25 17:31:10 +02:00
'description': description,
2016-07-25 17:35:12 +02:00
'creator': oembed_obj.get('author_name'),
'duration': parse_duration(oembed_obj.get('duration')),
2016-07-25 17:31:10 +02:00
'upload_date': upload_date,
'view_count': view_count,
}
2015-02-12 07:13:19 +01:00
class CamdemyFolderIE(InfoExtractor):
2016-09-08 13:29:05 +02:00
_VALID_URL = r'https?://(?:www\.)?camdemy\.com/folder/(?P<id>\d+)'
2015-02-12 07:13:19 +01:00
_TESTS = [{
# links with trailing slash
'url': 'http://www.camdemy.com/folder/450',
'info_dict': {
'id': '450',
'title': '信號與系統 2012 & 2011 (Signals and Systems)',
},
'playlist_mincount': 145
}, {
# links without trailing slash
# and multi-page
'url': 'http://www.camdemy.com/folder/853',
'info_dict': {
'id': '853',
'title': '科學計算 - 使用 Matlab'
},
'playlist_mincount': 20
}, {
# with displayMode parameter. For testing the codes to add parameters
'url': 'http://www.camdemy.com/folder/853/?displayMode=defaultOrderByOrg',
'info_dict': {
'id': '853',
'title': '科學計算 - 使用 Matlab'
},
'playlist_mincount': 20
}]
def _real_extract(self, url):
folder_id = self._match_id(url)
# Add displayMode=list so that all links are displayed in a single page
2015-02-12 07:23:25 +01:00
parsed_url = list(compat_urlparse.urlparse(url))
query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
2015-02-12 07:13:19 +01:00
query.update({'displayMode': 'list'})
parsed_url[4] = compat_urllib_parse_urlencode(query)
2015-02-12 07:23:25 +01:00
final_url = compat_urlparse.urlunparse(parsed_url)
2015-02-12 07:13:19 +01:00
page = self._download_webpage(final_url, folder_id)
matches = re.findall(r"href='(/media/\d+/?)'", page)
entries = [self.url_result('http://www.camdemy.com' + media_path)
for media_path in matches]
folder_title = self._html_search_meta('keywords', page)
return self.playlist_result(entries, folder_id, folder_title)