From ccaf6ca02c5bdc63f78e01a66429afaa5fb3cb68 Mon Sep 17 00:00:00 2001 From: Marc Abonce Seguin Date: Wed, 26 Jun 2019 00:45:20 -0500 Subject: [fix] update xpaths for new google results page --- searx/engines/google.py | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'searx') diff --git a/searx/engines/google.py b/searx/engines/google.py index 19bde710d..eed3a044e 100644 --- a/searx/engines/google.py +++ b/searx/engines/google.py @@ -107,13 +107,12 @@ images_path = '/images' supported_languages_url = 'https://www.google.com/preferences?#languages' # specific xpath variables -results_xpath = '//div[@class="g"]' -url_xpath = './/h3/a/@href' -title_xpath = './/h3' -content_xpath = './/span[@class="st"]' -content_misc_xpath = './/div[@class="f slp"]' -suggestion_xpath = '//p[@class="_Bmc"]' -spelling_suggestion_xpath = '//a[@class="spell"]' +results_xpath = '//div[contains(@class, "ZINbbc")]' +url_xpath = './/div[@class="kCrYT"][1]/a/@href' +title_xpath = './/div[@class="kCrYT"][1]/a/div[1]' +content_xpath = './/div[@class="kCrYT"][2]//div[contains(@class, "BNeawe")]//div[contains(@class, "BNeawe")]' +suggestion_xpath = '//div[contains(@class, "ZINbbc")][last()]//div[@class="rVLSBd"]/a//div[contains(@class, "BNeawe")]' +spelling_suggestion_xpath = '//div[@id="scc"]//a' # map : detail location map_address_xpath = './/div[@class="s"]//table//td[2]/span/text()' @@ -199,10 +198,6 @@ def request(query, params): params['headers']['Accept-Language'] = language + ',' + language + '-' + country params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' - # Force Safari 3.1 on Mac OS X (Leopard) user agent to avoid loading the new UI that Searx can't parse - params['headers']['User-Agent'] = ("Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_4)" - "AppleWebKit/525.18 (KHTML, like Gecko) Version/3.1.2 Safari/525.20.1") - params['google_hostname'] = google_hostname return params @@ -274,9 +269,7 @@ def response(resp): content = extract_text_from_dom(result, content_xpath) if content is None: continue - content_misc = extract_text_from_dom(result, content_misc_xpath) - if content_misc is not None: - content = content_misc + "
" + content + # append result results.append({'url': url, 'title': title, -- cgit v1.2.3 From f34ac58752b3857468d01c79d7bc3409e8b03fe3 Mon Sep 17 00:00:00 2001 From: Dalf Date: Tue, 6 Aug 2019 11:41:16 +0200 Subject: [mod] tidy oscar HTML output --- searx/templates/oscar/advanced.html | 9 +- searx/templates/oscar/base.html | 21 +- searx/templates/oscar/categories.html | 18 +- searx/templates/oscar/infobox.html | 33 +-- searx/templates/oscar/languages.html | 14 +- searx/templates/oscar/macros.html | 46 +-- searx/templates/oscar/navbar.html | 16 +- .../templates/oscar/result_templates/default.html | 62 ++-- searx/templates/oscar/result_templates/images.html | 85 +++--- searx/templates/oscar/results.html | 312 ++++++++++----------- searx/templates/oscar/search.html | 48 ++-- searx/templates/oscar/time-range.html | 22 +- 12 files changed, 339 insertions(+), 347 deletions(-) (limited to 'searx') diff --git a/searx/templates/oscar/advanced.html b/searx/templates/oscar/advanced.html index 95d99ba6a..bf5f86324 100644 --- a/searx/templates/oscar/advanced.html +++ b/searx/templates/oscar/advanced.html @@ -1,16 +1,17 @@ -