From 3501423dfec657892e54ffe00a02da3babdfe8e4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Mon, 10 Feb 2014 20:31:08 +0100 Subject: [PATCH] [googleplus] Modernize and simplify --- youtube_dl/extractor/googleplus.py | 59 ++++++++++++++---------------- 1 file changed, 27 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py index 2570746b2..cc29a7e5d 100644 --- a/youtube_dl/extractor/googleplus.py +++ b/youtube_dl/extractor/googleplus.py @@ -1,4 +1,5 @@ # coding: utf-8 +from __future__ import unicode_literals import datetime import re @@ -10,32 +11,28 @@ from ..utils import ( class GooglePlusIE(InfoExtractor): - IE_DESC = u'Google Plus' - _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' - IE_NAME = u'plus.google' + IE_DESC = 'Google Plus' + _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P\w+)' + IE_NAME = 'plus.google' _TEST = { - u"url": u"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH", - u"file": u"ZButuJc6CtH.flv", - u"info_dict": { - u"upload_date": u"20120613", - u"uploader": u"井上ヨシマサ", - u"title": u"嘆きの天使 降臨" + 'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH', + 'info_dict': { + 'id': 'ZButuJc6CtH', + 'ext': 'flv', + 'upload_date': '20120613', + 'uploader': '井上ヨシマサ', + 'title': '嘆きの天使 降臨', } } def _real_extract(self, url): # Extract id from URL mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - post_url = mobj.group(0) - video_id = mobj.group(1) - - video_extension = 'flv' + video_id = mobj.group('id') # Step 1, Retrieve post webpage to extract further information - webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage') + webpage = self._download_webpage(url, video_id, 'Downloading entry webpage') self.report_extraction(video_id) @@ -43,7 +40,7 @@ class GooglePlusIE(InfoExtractor): upload_date = self._html_search_regex( r'''(?x) ([0-9]{4}-[0-9]{2}-[0-9]{2})''', - webpage, u'upload date', fatal=False, flags=re.VERBOSE) + webpage, 'upload date', fatal=False, flags=re.VERBOSE) if upload_date: # Convert timestring to a format suitable for filename upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") @@ -51,28 +48,27 @@ class GooglePlusIE(InfoExtractor): # Extract uploader uploader = self._html_search_regex(r'rel\="author".*?>(.*?)', - webpage, u'uploader', fatal=False) + webpage, 'uploader', fatal=False) # Extract title # Get the first line for title video_title = self._html_search_regex(r'