jandieman/searxng
2
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2025-12-22 19:50:00 +00:00
Code Issues Projects Releases Wiki Activity

[mod] various engines: use eval_xpath* functions and searx.exceptions.*

Browse Source 
Engine list: ahmia, duckduckgo_images, elasticsearch, google, google_images, google_videos, youtube_api
This commit is contained in:
Alexandre Flament
2020-11-26 17:22:54 +01:00
parent ad72803ed9
commit 64cccae99e
7 changed files with 44 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
searx/engines/google_videos.py
View File

@@ -13,7 +13,7 @@
from datetime import date, timedelta
from urllib.parse import urlencode
from lxml import html
from searx.utils import extract_text
from searx.utils import extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex
import re
# engine dependent config
@@ -66,11 +66,11 @@ def response(resp):
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath('//div[@class="g"]'):
for result in eval_xpath_list(dom, '//div[@class="g"]'):
title = extract_text(result.xpath('.//h3'))
url = result.xpath('.//div[@class="r"]/a/@href')[0]
content = extract_text(result.xpath('.//span[@class="st"]'))
title = extract_text(eval_xpath(result, './/h3'))
url = eval_xpath_getindex(result, './/div[@class="r"]/a/@href', 0)
content = extract_text(eval_xpath(result, './/span[@class="st"]'))
# get thumbnails
script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)