From 895ba7d1dd5b92259272198976d150847014b644 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 29 Jul 2014 05:59:47 +0200 Subject: [PATCH] [gamestar] Use helper methods to not break if something changes (#3393) --- youtube_dl/extractor/gamestar.py | 34 +++++++++++++++++++------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/gamestar.py b/youtube_dl/extractor/gamestar.py index 5c9decdea..50f8fc7e7 100644 --- a/youtube_dl/extractor/gamestar.py +++ b/youtube_dl/extractor/gamestar.py @@ -4,6 +4,13 @@ import re from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + str_to_int, + unified_strdate, +) + class GameStarIE(InfoExtractor): _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P[0-9]+)\.html' @@ -34,25 +41,24 @@ def _real_extract(self, url): description = self._og_search_description(webpage).strip() - og_thumbnail = self._og_search_thumbnail(webpage) - thumbnail = 'http:' + og_thumbnail + thumbnail = self._proto_relative_url( + self._og_search_thumbnail(webpage), scheme='http:') - upload_date_raw = self._html_search_regex( + upload_date = unified_strdate(self._html_search_regex( r'Datum: ([0-9]+\.[0-9]+\.[0-9]+)  ', - webpage, 'upload_date').split('.') - upload_date = upload_date_raw[2] + upload_date_raw[1] + upload_date_raw[0] + webpage, 'upload_date', fatal=False)) - duration_raw = self._html_search_regex( - r'  Länge: ([0-9]+:[0-9]+)', webpage, 'duration').split(':') - duration = int(duration_raw[0])*60 + int(duration_raw[1]) + duration = parse_duration(self._html_search_regex( + r'  Länge: ([0-9]+:[0-9]+)', webpage, 'duration', + fatal=False)) - view_count_raw = self._html_search_regex( - r'  Zuschauer: ([0-9\.]+)  ', webpage, 'view_count') - view_count = int(view_count_raw.replace('.', '')) + view_count = str_to_int(self._html_search_regex( + r'  Zuschauer: ([0-9\.]+)  ', webpage, + 'view_count', fatal=False)) - comment_count_raw = self._html_search_regex( - r'>Kommentieren \(([0-9]+)\)', webpage, 'comment_count') - comment_count = int(comment_count_raw) + comment_count = int_or_none(self._html_search_regex( + r'>Kommentieren \(([0-9]+)\)', webpage, 'comment_count', + fatal=False)) return { 'id': video_id,