From 8708d764252a83e650f36fe47f89ace4f2a91a5b Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Wed, 11 Feb 2015 16:39:15 +0800 Subject: [PATCH] [camdemy] Add new extractor Single file download done, while folder extaction in plan --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/camdemy.py | 78 ++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) create mode 100644 youtube_dl/extractor/camdemy.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index da3b2b2d0..496e4d0b7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -49,6 +49,7 @@ 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 diff --git a/youtube_dl/extractor/camdemy.py b/youtube_dl/extractor/camdemy.py new file mode 100644 index 000000000..54959f2cf --- /dev/null +++ b/youtube_dl/extractor/camdemy.py @@ -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\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"
Posted :
.*
([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"
Views :
.*
([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, + }