kamp/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-11-23 04:27:46 +01:00
Code

[fix] update digg engine

Browse Source
This commit is contained in:
Adam Tauber 2019-10-16 15:11:27 +02:00
parent 72459b246b
commit 1057e42cfd
1 changed files with 12 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
searx/engines/digg.py
View File

@ -15,7 +15,8 @@ import string
from dateutil import parser from dateutil import parser
from json import loads from json import loads
from lxml import html from lxml import html
from searx.url_utils import quote_plus from searx.url_utils import urlencode
from datetime import datetime
# engine dependent config # engine dependent config
categories = ['news', 'social media'] categories = ['news', 'social media']
@ -23,7 +24,7 @@ paging = True
# search-url # search-url
base_url = 'https://digg.com/' base_url = 'https://digg.com/'
search_url = base_url + 'api/search/{query}.json?position={position}&format=html' search_url = base_url + 'api/search/?{query}&from={position}&size=20&format=html'
# specific xpath variables # specific xpath variables
results_xpath = '//article' results_xpath = '//article'
@ -38,9 +39,9 @@ digg_cookie_chars = string.ascii_uppercase + string.ascii_lowercase +\
# do search-request # do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * 10 offset = (params['pageno'] - 1) * 20
params['url'] = search_url.format(position=offset, params['url'] = search_url.format(position=offset,
query=quote_plus(query)) query=urlencode({'q': query}))
params['cookies']['frontend.auid'] = ''.join(random.choice( params['cookies']['frontend.auid'] = ''.join(random.choice(
digg_cookie_chars) for _ in range(22)) digg_cookie_chars) for _ in range(22))
return params return params
@ -52,30 +53,17 @@ def response(resp):
search_result = loads(resp.text) search_result = loads(resp.text)
if 'html' not in search_result or search_result['html'] == '':
return results
dom = html.fromstring(search_result['html'])
# parse results # parse results
for result in dom.xpath(results_xpath): for result in search_result['mapped']:
url = result.attrib.get('data-contenturl')
thumbnail = result.xpath('.//img')[0].attrib.get('src')
title = ''.join(result.xpath(title_xpath))
content = ''.join(result.xpath(content_xpath))
pubdate = result.xpath(pubdate_xpath)[0].attrib.get('datetime')
publishedDate = parser.parse(pubdate)
# http to https
thumbnail = thumbnail.replace("http://static.digg.com", "https://static.digg.com")
published = datetime.strptime(result['created']['ISO'], "%Y-%m-%d %H:%M:%S")
# append result # append result
results.append({'url': url, results.append({'url': result['url'],
'title': title, 'title': result['title'],
'content': content, 'content': result['excerpt'],
'template': 'videos.html', 'template': 'videos.html',
'publishedDate': publishedDate, 'publishedDate': published,
'thumbnail': thumbnail}) 'thumbnail': result['images']['thumbImage']})
# return results # return results
return results return results