From ad72803ed98760b2a95690dea3b95eacc670427c Mon Sep 17 00:00:00 2001 From: Alexandre Flament Date: Thu, 26 Nov 2020 15:49:33 +0100 Subject: [PATCH] [mod] xpath, 1337x, acgsou, apkmirror, archlinux, arxiv: use eval_xpath_* functions --- searx/engines/1337x.py | 14 +++++++------- searx/engines/acgsou.py | 27 ++++++++++++--------------- searx/engines/apkmirror.py | 9 +++++---- searx/engines/archlinux.py | 6 +++--- searx/engines/arxiv.py | 20 +++++++++----------- searx/engines/xpath.py | 29 +++++++++++++++-------------- 6 files changed, 51 insertions(+), 54 deletions(-) diff --git a/searx/engines/1337x.py b/searx/engines/1337x.py index 9e045bc51..18478876a 100644 --- a/searx/engines/1337x.py +++ b/searx/engines/1337x.py @@ -1,6 +1,6 @@ from urllib.parse import quote, urljoin from lxml import html -from searx.utils import extract_text, get_torrent_size +from searx.utils import extract_text, get_torrent_size, eval_xpath, eval_xpath_list, eval_xpath_getindex url = 'https://1337x.to/' @@ -20,12 +20,12 @@ def response(resp): dom = html.fromstring(resp.text) - for result in dom.xpath('//table[contains(@class, "table-list")]/tbody//tr'): - href = urljoin(url, result.xpath('./td[contains(@class, "name")]/a[2]/@href')[0]) - title = extract_text(result.xpath('./td[contains(@class, "name")]/a[2]')) - seed = extract_text(result.xpath('.//td[contains(@class, "seeds")]')) - leech = extract_text(result.xpath('.//td[contains(@class, "leeches")]')) - filesize_info = extract_text(result.xpath('.//td[contains(@class, "size")]/text()')) + for result in eval_xpath_list(dom, '//table[contains(@class, "table-list")]/tbody//tr'): + href = urljoin(url, eval_xpath_getindex(result, './td[contains(@class, "name")]/a[2]/@href', 0)) + title = extract_text(eval_xpath(result, './td[contains(@class, "name")]/a[2]')) + seed = extract_text(eval_xpath(result, './/td[contains(@class, "seeds")]')) + leech = extract_text(eval_xpath(result, './/td[contains(@class, "leeches")]')) + filesize_info = extract_text(eval_xpath(result, './/td[contains(@class, "size")]/text()')) filesize, filesize_multiplier = filesize_info.split() filesize = get_torrent_size(filesize, filesize_multiplier) diff --git a/searx/engines/acgsou.py b/searx/engines/acgsou.py index a436df283..b8b367c24 100644 --- a/searx/engines/acgsou.py +++ b/searx/engines/acgsou.py @@ -11,7 +11,7 @@ from urllib.parse import urlencode from lxml import html -from searx.utils import extract_text, get_torrent_size +from searx.utils import extract_text, get_torrent_size, eval_xpath_list, eval_xpath_getindex # engine dependent config categories = ['files', 'images', 'videos', 'music'] @@ -37,29 +37,26 @@ def request(query, params): def response(resp): results = [] dom = html.fromstring(resp.text) - for result in dom.xpath(xpath_results): + for result in eval_xpath_list(dom, xpath_results): # defaults filesize = 0 magnet_link = "magnet:?xt=urn:btih:{}&tr=http://tracker.acgsou.com:2710/announce" - try: - category = extract_text(result.xpath(xpath_category)[0]) - except: - pass - - page_a = result.xpath(xpath_title)[0] + category = extract_text(eval_xpath_getindex(result, xpath_category, 0, default=[])) + page_a = eval_xpath_getindex(result, xpath_title, 0) title = extract_text(page_a) href = base_url + page_a.attrib.get('href') magnet_link = magnet_link.format(page_a.attrib.get('href')[5:-5]) - try: - filesize_info = result.xpath(xpath_filesize)[0] - filesize = filesize_info[:-2] - filesize_multiplier = filesize_info[-2:] - filesize = get_torrent_size(filesize, filesize_multiplier) - except: - pass + filesize_info = eval_xpath_getindex(result, xpath_filesize, 0, default=None) + if filesize_info: + try: + filesize = filesize_info[:-2] + filesize_multiplier = filesize_info[-2:] + filesize = get_torrent_size(filesize, filesize_multiplier) + except: + pass # I didn't add download/seed/leech count since as I figured out they are generated randomly everytime content = 'Category: "{category}".' content = content.format(category=category) diff --git a/searx/engines/apkmirror.py b/searx/engines/apkmirror.py index a8ff499af..3a948dcb4 100644 --- a/searx/engines/apkmirror.py +++ b/searx/engines/apkmirror.py @@ -11,7 +11,7 @@ from urllib.parse import urlencode from lxml import html -from searx.utils import extract_text +from searx.utils import extract_text, eval_xpath_list, eval_xpath_getindex # engine dependent config @@ -42,12 +42,13 @@ def response(resp): dom = html.fromstring(resp.text) # parse results - for result in dom.xpath('.//div[@id="content"]/div[@class="listWidget"]/div[@class="appRow"]'): + for result in eval_xpath_list(dom, './/div[@id="content"]/div[@class="listWidget"]/div[@class="appRow"]'): - link = result.xpath('.//h5/a')[0] + link = eval_xpath_getindex(result, './/h5/a', 0) url = base_url + link.attrib.get('href') + '#downloads' title = extract_text(link) - thumbnail_src = base_url + result.xpath('.//img')[0].attrib.get('src').replace('&w=32&h=32', '&w=64&h=64') + thumbnail_src = base_url\ + + eval_xpath_getindex(result, './/img', 0).attrib.get('src').replace('&w=32&h=32', '&w=64&h=64') res = { 'url': url, diff --git a/searx/engines/archlinux.py b/searx/engines/archlinux.py index 8f93f4f38..04117c07d 100644 --- a/searx/engines/archlinux.py +++ b/searx/engines/archlinux.py @@ -13,7 +13,7 @@ from urllib.parse import urlencode, urljoin from lxml import html -from searx.utils import extract_text +from searx.utils import extract_text, eval_xpath_list, eval_xpath_getindex # engine dependent config categories = ['it'] @@ -131,8 +131,8 @@ def response(resp): dom = html.fromstring(resp.text) # parse results - for result in dom.xpath(xpath_results): - link = result.xpath(xpath_link)[0] + for result in eval_xpath_list(dom, xpath_results): + link = eval_xpath_getindex(result, xpath_link, 0) href = urljoin(base_url, link.attrib.get('href')) title = extract_text(link) diff --git a/searx/engines/arxiv.py b/searx/engines/arxiv.py index 6e231c382..c702c5987 100644 --- a/searx/engines/arxiv.py +++ b/searx/engines/arxiv.py @@ -13,6 +13,7 @@ from lxml import html from datetime import datetime +from searx.utils import eval_xpath_list, eval_xpath_getindex categories = ['science'] @@ -42,29 +43,26 @@ def response(resp): results = [] dom = html.fromstring(resp.content) - search_results = dom.xpath('//entry') - for entry in search_results: - title = entry.xpath('.//title')[0].text + for entry in eval_xpath_list(dom, '//entry'): + title = eval_xpath_getindex(entry, './/title', 0).text - url = entry.xpath('.//id')[0].text + url = eval_xpath_getindex(entry, './/id', 0).text content_string = '{doi_content}{abstract_content}' - abstract = entry.xpath('.//summary')[0].text + abstract = eval_xpath_getindex(entry, './/summary', 0).text # If a doi is available, add it to the snipppet - try: - doi_content = entry.xpath('.//link[@title="doi"]')[0].text - content = content_string.format(doi_content=doi_content, abstract_content=abstract) - except: - content = content_string.format(doi_content="", abstract_content=abstract) + doi_element = eval_xpath_getindex(entry, './/link[@title="doi"]', 0, default=None) + doi_content = doi_element.text if doi_element is not None else '' + content = content_string.format(doi_content=doi_content, abstract_content=abstract) if len(content) > 300: content = content[0:300] + "..." # TODO: center snippet on query term - publishedDate = datetime.strptime(entry.xpath('.//published')[0].text, '%Y-%m-%dT%H:%M:%SZ') + publishedDate = datetime.strptime(eval_xpath_getindex(entry, './/published', 0).text, '%Y-%m-%dT%H:%M:%SZ') res_dict = {'url': url, 'title': title, diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py index a569d9160..d420e250a 100644 --- a/searx/engines/xpath.py +++ b/searx/engines/xpath.py @@ -1,6 +1,6 @@ from lxml import html from urllib.parse import urlencode -from searx.utils import extract_text, extract_url, eval_xpath +from searx.utils import extract_text, extract_url, eval_xpath, eval_xpath_list search_url = None url_xpath = None @@ -42,21 +42,22 @@ def response(resp): is_onion = True if 'onions' in categories else False if results_xpath: - for result in eval_xpath(dom, results_xpath): - url = extract_url(eval_xpath(result, url_xpath), search_url) - title = extract_text(eval_xpath(result, title_xpath)) - content = extract_text(eval_xpath(result, content_xpath)) + for result in eval_xpath_list(dom, results_xpath): + url = extract_url(eval_xpath_list(result, url_xpath, min_len=1), search_url) + title = extract_text(eval_xpath_list(result, title_xpath, min_len=1)) + content = extract_text(eval_xpath_list(result, content_xpath, min_len=1)) tmp_result = {'url': url, 'title': title, 'content': content} # add thumbnail if available if thumbnail_xpath: - thumbnail_xpath_result = eval_xpath(result, thumbnail_xpath) + thumbnail_xpath_result = eval_xpath_list(result, thumbnail_xpath) if len(thumbnail_xpath_result) > 0: tmp_result['img_src'] = extract_url(thumbnail_xpath_result, search_url) # add alternative cached url if available if cached_xpath: - tmp_result['cached_url'] = cached_url + extract_text(result.xpath(cached_xpath)) + tmp_result['cached_url'] = cached_url\ + + extract_text(eval_xpath_list(result, cached_xpath, min_len=1)) if is_onion: tmp_result['is_onion'] = True @@ -66,19 +67,19 @@ def response(resp): if cached_xpath: for url, title, content, cached in zip( (extract_url(x, search_url) for - x in dom.xpath(url_xpath)), - map(extract_text, dom.xpath(title_xpath)), - map(extract_text, dom.xpath(content_xpath)), - map(extract_text, dom.xpath(cached_xpath)) + x in eval_xpath_list(dom, url_xpath)), + map(extract_text, eval_xpath_list(dom, title_xpath)), + map(extract_text, eval_xpath_list(dom, content_xpath)), + map(extract_text, eval_xpath_list(dom, cached_xpath)) ): results.append({'url': url, 'title': title, 'content': content, 'cached_url': cached_url + cached, 'is_onion': is_onion}) else: for url, title, content in zip( (extract_url(x, search_url) for - x in dom.xpath(url_xpath)), - map(extract_text, dom.xpath(title_xpath)), - map(extract_text, dom.xpath(content_xpath)) + x in eval_xpath_list(dom, url_xpath)), + map(extract_text, eval_xpath_list(dom, title_xpath)), + map(extract_text, eval_xpath_list(dom, content_xpath)) ): results.append({'url': url, 'title': title, 'content': content, 'is_onion': is_onion})