From cf26aba93b96bb1171feb60fefb232a9113b85b0 Mon Sep 17 00:00:00 2001 From: Venca24 Date: Fri, 4 Jan 2019 15:48:22 +0100 Subject: [PATCH] [FIX] google videos thumbnails --- searx/engines/google_videos.py | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/searx/engines/google_videos.py b/searx/engines/google_videos.py index 53acf517d..aa8507988 100644 --- a/searx/engines/google_videos.py +++ b/searx/engines/google_videos.py @@ -7,15 +7,16 @@ @using-api no @results HTML @stable no - @parse url, title, content + @parse url, title, content, thumbnail """ from datetime import date, timedelta from json import loads from lxml import html +from searx.engines import logger from searx.engines.xpath import extract_text from searx.url_utils import urlencode - +import re # engine dependent config categories = ['videos'] @@ -73,11 +74,24 @@ def response(resp): url = result.xpath('.//div[@class="r"]/a/@href')[0] content = extract_text(result.xpath('.//span[@class="st"]')) + # get thumbnails + script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text) + id = result.xpath('.//div[@class="s"]//img/@id')[0] + thumbnails_data = re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id, + script) + logger.debug('google video engine: ' + id + ' matched ' + str(len(thumbnails_data)) + ' times (thumbnail)') + tmp = [] + if len(thumbnails_data) != 0: + tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0]) + thumbnail = '' + if len(tmp) != 0: + thumbnail = tmp[-1] + # append result results.append({'url': url, 'title': title, 'content': content, - 'thumbnail': '', + 'thumbnail': thumbnail, 'template': 'videos.html'}) return results