From 8883aed1327a84a81cfabe90419c27259be12fb6 Mon Sep 17 00:00:00 2001 From: ta Date: Fri, 17 Jun 2022 16:13:10 +0700 Subject: [PATCH] [fix] google play apps engine: implement engines/google_play_apps.py --- searx/engines/google_play_apps.py | 68 +++++++++++++++++++++++++++++++ searx/settings.yml | 16 +------- 2 files changed, 69 insertions(+), 15 deletions(-) create mode 100644 searx/engines/google_play_apps.py diff --git a/searx/engines/google_play_apps.py b/searx/engines/google_play_apps.py new file mode 100644 index 000000000..577e4e114 --- /dev/null +++ b/searx/engines/google_play_apps.py @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: AGPL-3.0-or-later +""" + Google Play Apps +""" + +from urllib.parse import urlencode +from lxml import html +from searx.utils import ( + eval_xpath, + extract_url, + extract_text, + eval_xpath_list, + eval_xpath_getindex, +) + +about = { + "website": "https://play.google.com/", + "wikidata_id": "Q79576", + "use_official_api": False, + "require_api_key": False, + "results": "HTML", +} + +categories = ["files", "apps"] +search_url = "https://play.google.com/store/search?{query}&c=apps" + + +def request(query, params): + params["url"] = search_url.format(query=urlencode({"q": query})) + + return params + + +def response(resp): + results = [] + + dom = html.fromstring(resp.text) + + if eval_xpath(dom, '//div[@class="v6DsQb"]'): + return [] + + spot = eval_xpath_getindex(dom, '//div[@class="ipRz4"]', 0, None) + if spot is not None: + url = extract_url(eval_xpath(spot, './a[@class="Qfxief"]/@href'), search_url) + title = extract_text(eval_xpath(spot, './/div[@class="vWM94c"]')) + content = extract_text(eval_xpath(spot, './/div[@class="LbQbAe"]')) + img = extract_text(eval_xpath(spot, './/img[@class="T75of bzqKMd"]/@src')) + + results.append({"url": url, "title": title, "content": content, "img_src": img}) + + more = eval_xpath_list(dom, '//c-wiz[@jsrenderer="RBsfwb"]//div[@role="listitem"]', min_len=1) + for result in more: + url = extract_url(eval_xpath(result, ".//a/@href"), search_url) + title = extract_text(eval_xpath(result, './/span[@class="DdYX5"]')) + content = extract_text(eval_xpath(result, './/span[@class="wMUdtb"]')) + img = extract_text( + eval_xpath( + result, + './/img[@class="T75of stzEZd" or @class="T75of etjhNc Q8CSx "]/@src', + ) + ) + + results.append({"url": url, "title": title, "content": content, "img_src": img}) + + for suggestion in eval_xpath_list(dom, '//c-wiz[@jsrenderer="qyd4Kb"]//div[@class="ULeU3b neq64b"]'): + results.append({"suggestion": extract_text(eval_xpath(suggestion, './/div[@class="Epkrse "]'))}) + + return results diff --git a/searx/settings.yml b/searx/settings.yml index a6311b7ff..bc4055f03 100644 --- a/searx/settings.yml +++ b/searx/settings.yml @@ -705,23 +705,9 @@ engines: shortcut: gos - name: google play apps - engine: xpath - search_url: https://play.google.com/store/search?q={query}&c=apps - results_xpath: '//div[@class="ImZGtf mpg5gc"]' - title_xpath: './/div[@class="RZEgze"]//div[@class="kCSSQe"]//a' - url_xpath: './/div[@class="RZEgze"]//div[@class="kCSSQe"]//a/@href' - content_xpath: './/div[@class="RZEgze"]//a[@class="mnKHRc"]' - thumbnail_xpath: './/div[@class="uzcko"]/div/span[1]//img/@data-src' - categories: [files, apps] + engine: google_play_apps shortcut: gpa disabled: true - about: - website: https://play.google.com/ - wikidata_id: Q79576 - official_api_documentation: - use_official_api: false - require_api_key: false - results: HTML - name: google play movies engine: xpath