From 7332ce6d5f72305f1589383c6694e030821d4d86 Mon Sep 17 00:00:00 2001 From: neodarz Date: Tue, 20 Dec 2016 19:10:39 +0100 Subject: Initial release :) --- khaganatForum.py | 131 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 131 insertions(+) create mode 100644 khaganatForum.py (limited to 'khaganatForum.py') diff --git a/khaganatForum.py b/khaganatForum.py new file mode 100644 index 0000000..75cd0be --- /dev/null +++ b/khaganatForum.py @@ -0,0 +1,131 @@ +# Doku Wiki +# +# @website https://www.dokuwiki.org/ +# @provide-api yes +# (https://www.dokuwiki.org/devel:xmlrpc) +# +# @using-api no +# @results HTML +# @stable yes +# @parse (general) url, title, content + +from urllib import urlencode +from lxml.html import fromstring +from searx.engines.xpath import extract_text +from datetime import datetime + +# engine dependent config +categories = ['general'] # TODO , 'images', 'music', 'videos', 'files' +paging = False +language_support = False +number_of_results = 5 + +# search-url +# Doku is OpenSearch compatible +base_url = 'https://khaganat.net' +search_url = '/forum/index.php?action=search2&{query}' +#search_url = '/wikhan/?do=search'\ +# '&{query}' +# TODO '&startRecord={offset}'\ +# TODO '&maximumRecords={limit}'\ + + +# do search-request +def request(query, params): + + params['url'] = base_url +\ + search_url.format(query=urlencode({'search': query})) + + return params + + +# get response from search-request +def response(resp): + results = [] + + doc = fromstring(resp.text) + + # parse results + # Quickhits + for r in doc.xpath('//div[@id="main_content_section"]/div/div/div'): + try: + res_url = r.xpath('.//div[@class="topic_details floatleft"]/h5/a/@href')[-1] + except: + continue + + if not res_url: + continue + + #content = extract_text(r.xpath('.//div[@class="list_posts"]')) + title = extract_text(r.xpath('.//div[@class="topic_details floatleft"]/h5')) + + + + #dataBrut = extract_text(r.xpath('.//span[@class="date"]')) + + #data = dataBrut.split('-') + + + + #date = '-'.join(dataS) + #adatetime = data[1] + #data = adatetime.split(',') + #date = data[1] + #Thedate = dataBrut.split(' ') + #TheDay = Thedate[1].split(',') + + + #if Thedate[0] == "Jan": + # ThedateMonth = 1 + #elif Thedate[0] == "Feb": + # ThedateMonth = 2 + #elif Thedate[0] == "Mar": + # ThedateMonth = 3 + #elif Thedate[0] == "Apr": + # ThedateMonth = 4 + #elif Thedate[0] == "May": + # ThedateMonth = 5 + #elif Thedate[0] == "Jun": + # ThedateMonth = 6 + #elif Thedate[0] == "Jul": + # ThedateMonth = 7 + #elif Thedate[0] == "Aug": + # ThedateMonth = 8 + #elif Thedate[0] == "Sep": + # ThedateMonth = 9 + #elif Thedate[0] == "Oct": + # ThedateMonth = 10 + #elif Thedate[0] == "Nov": + # ThedateMonth = 11 + #else: + # ThedateMonth = 12 + + # append result + results.append({'title': title, + 'content': "", + 'url': base_url + res_url}) + #'publishedDate': datetime(int(Thedate[2]), ThedateMonth, int(TheDay[0]), 3, 1, 42)}) + + + + # Search results + #for r in doc.xpath('//dl[@class="search_results"]/*'): + # try: + # if r.tag == "dt": + # res_url = r.xpath('.//a[@class="wikilink1"]/@href')[-1] + # title = extract_text(r.xpath('.//a[@class="wikilink1"]/@title')) + # elif r.tag == "dd": + # content = extract_text(r.xpath('.')) + + # append result + # results.append({'title': title, + # 'content': content, + # 'url': base_url + res_url}) + # except: + # continue + + # if not res_url: + # continue + + # return results + return results -- cgit v1.2.1