searxngRebrandZaclys/searx/engines/digg.py
Markus Heiser 6b0a896f01 [mod] digg - pylint searx/engines/digg.py
Eliminate redundant file names which are tested by test.pylint and ignored by
test.pep8

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2020-12-02 20:59:30 +01:00

70 lines
1.9 KiB
Python

"""
Digg (News, Social media)
@website https://digg.com/
@provide-api no
@using-api no
@results HTML (using search portal)
@stable no (HTML can change)
@parse url, title, content, publishedDate, thumbnail
"""
# pylint: disable=missing-function-docstring
import random
import string
from json import loads
from urllib.parse import urlencode
from datetime import datetime
# engine dependent config
categories = ['news', 'social media']
paging = True
# search-url
base_url = 'https://digg.com/'
search_url = base_url + 'api/search/?{query}&from={position}&size=20&format=html'
# specific xpath variables
results_xpath = '//article'
link_xpath = './/small[@class="time"]//a'
title_xpath = './/h2//a//text()'
content_xpath = './/p//text()'
pubdate_xpath = './/time'
digg_cookie_chars = string.ascii_uppercase + string.ascii_lowercase +\
string.digits + "+_"
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 20
params['url'] = search_url.format(position=offset,
query=urlencode({'q': query}))
params['cookies']['frontend.auid'] = ''.join(random.choice(
digg_cookie_chars) for _ in range(22))
return params
# get response from search-request
def response(resp):
results = []
search_result = loads(resp.text)
# parse results
for result in search_result['mapped']:
# 'created': {'ISO': '2020-10-16T14:09:55Z', ...}
published = datetime.strptime(result['created']['ISO'], "%Y-%m-%dT%H:%M:%SZ")
# append result
results.append({'url': result['url'],
'title': result['title'],
'content': result['excerpt'],
'template': 'videos.html',
'publishedDate': published,
'thumbnail': result['images']['thumbImage']})
# return results
return results