diff --git a/searx/engines/google_videos.py b/searx/engines/google_videos.py index 310b31490..9a41b2dfa 100644 --- a/searx/engines/google_videos.py +++ b/searx/engines/google_videos.py @@ -7,7 +7,7 @@ @using-api no @results HTML @stable no - @parse url, title, content + @parse url, title, content, thumbnail """ from datetime import date, timedelta @@ -15,7 +15,7 @@ from json import loads from lxml import html from searx.engines.xpath import extract_text from searx.url_utils import urlencode - +import re # engine dependent config categories = ['videos'] @@ -25,7 +25,7 @@ time_range_support = True number_of_results = 10 search_url = 'https://www.google.com/search'\ - '?{query}'\ + '?q={query}'\ '&tbm=vid'\ '&{search_options}' time_range_attr = "qdr:{range}" @@ -69,15 +69,27 @@ def response(resp): # parse results for result in dom.xpath('//div[@class="g"]'): - title = extract_text(result.xpath('.//h3/a')) - url = result.xpath('.//h3/a/@href')[0] + title = extract_text(result.xpath('.//h3')) + 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) + 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 diff --git a/tests/unit/engines/test_google_videos.py b/tests/unit/engines/test_google_videos.py index a48e9a755..3b7edf373 100644 --- a/tests/unit/engines/test_google_videos.py +++ b/tests/unit/engines/test_google_videos.py @@ -30,16 +30,34 @@ class TestGoogleVideosEngine(SearxTestCase):