[camdemy] Fix camdemy

This commit is contained in:
Sergey M․ 2016-07-25 22:31:10 +07:00
parent e8be2943a7
commit 59eaf69e33
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -1,7 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import datetime
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -10,8 +9,9 @@ from ..compat import (
compat_urlparse, compat_urlparse,
) )
from ..utils import ( from ..utils import (
parse_iso8601, clean_html,
str_to_int, str_to_int,
unified_strdate,
) )
@ -26,14 +26,13 @@ class CamdemyIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Ch1-1 Introduction, Signals (02-23-2012)', 'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'description': '',
'creator': 'ss11spring', 'creator': 'ss11spring',
'upload_date': '20130114', 'upload_date': '20130114',
'timestamp': 1358154556,
'view_count': int, 'view_count': int,
} }
}, { }, {
# With non-empty description # With non-empty description
# webpage returns "No permission or not login"
'url': 'http://www.camdemy.com/media/13885', 'url': 'http://www.camdemy.com/media/13885',
'md5': '4576a3bb2581f86c61044822adbd1249', 'md5': '4576a3bb2581f86c61044822adbd1249',
'info_dict': { 'info_dict': {
@ -41,33 +40,34 @@ class CamdemyIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'EverCam + Camdemy QuickStart', 'title': 'EverCam + Camdemy QuickStart',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'description': 'md5:050b62f71ed62928f8a35f1a41e186c9', 'description': 'md5:2a9f989c2b153a2342acee579c6e7db6',
'creator': 'evercam', 'creator': 'evercam',
'upload_date': '20140620',
'timestamp': 1403271569,
} }
}, { }, {
# External source # External source (YouTube)
'url': 'http://www.camdemy.com/media/14842', 'url': 'http://www.camdemy.com/media/14842',
'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7',
'info_dict': { 'info_dict': {
'id': '2vsYQzNIsJo', 'id': '2vsYQzNIsJo',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Excel 2013 Tutorial - How to add Password Protection',
'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
'upload_date': '20130211', 'upload_date': '20130211',
'uploader': 'Hun Kim', 'uploader': 'Hun Kim',
'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
'uploader_id': 'hunkimtutorials', 'uploader_id': 'hunkimtutorials',
'title': 'Excel 2013 Tutorial - How to add Password Protection', },
} 'params': {
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
page = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id)
src_from = self._html_search_regex( src_from = self._html_search_regex(
r"<div class='srcFrom'>Source: <a title='([^']+)'", page, r"class=['\"]srcFrom['\"][^>]*>Sources?(?:\s+from)?\s*:\s*<a[^>]+(?:href|title)=(['\"])(?P<url>(?:(?!\1).)+)\1",
'external source', default=None) webpage, 'external source', default=None, group='url')
if src_from: if src_from:
return self.url_result(src_from) return self.url_result(src_from)
@ -78,27 +78,31 @@ class CamdemyIE(InfoExtractor):
video_folder = compat_urlparse.urljoin(thumb_url, 'video/') video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
file_list_doc = self._download_xml( file_list_doc = self._download_xml(
compat_urlparse.urljoin(video_folder, 'fileList.xml'), compat_urlparse.urljoin(video_folder, 'fileList.xml'),
video_id, 'Filelist XML') video_id, 'Downloading filelist XML')
file_name = file_list_doc.find('./video/item/fileName').text file_name = file_list_doc.find('./video/item/fileName').text
video_url = compat_urlparse.urljoin(video_folder, file_name) video_url = compat_urlparse.urljoin(video_folder, file_name)
timestamp = parse_iso8601(self._html_search_regex( # Some URLs return "No permission or not login" in a webpage despite being
r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<", # freely available via oembed JSON URL (e.g. http://www.camdemy.com/media/13885)
page, 'creation time', fatal=False), upload_date = unified_strdate(self._search_regex(
delimiter=' ', timezone=datetime.timedelta(hours=8)) r'>published on ([^<]+)<', webpage,
view_count = str_to_int(self._html_search_regex( 'upload date', default=None))
r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<", view_count = str_to_int(self._search_regex(
page, 'view count', fatal=False)) 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 { return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': oembed_obj['title'], 'title': oembed_obj['title'],
'thumbnail': thumb_url, 'thumbnail': thumb_url,
'description': self._html_search_meta('description', page), 'description': description,
'creator': oembed_obj['author_name'], 'creator': oembed_obj['author_name'],
'duration': oembed_obj['duration'], 'duration': oembed_obj['duration'],
'timestamp': timestamp, 'upload_date': upload_date,
'view_count': view_count, 'view_count': view_count,
} }