2021-01-13 10:31:25 +00:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
2021-04-26 18:18:20 +00:00
|
|
|
# lint: pylint
|
2021-06-21 16:15:40 +00:00
|
|
|
"""This is the implementation of the google news engine. The google news API
|
|
|
|
ignores some parameters from the common :ref:`google API`:
|
2021-01-26 10:49:27 +00:00
|
|
|
|
|
|
|
- num_ : the number of search results is ignored
|
|
|
|
- save_ : is ignored / Google-News results are always *SafeSearch*
|
2021-01-22 17:49:45 +00:00
|
|
|
|
|
|
|
.. _num: https://developers.google.com/custom-search/docs/xml_results#numsp
|
2021-01-26 10:49:27 +00:00
|
|
|
.. _save: https://developers.google.com/custom-search/docs/xml_results#safesp
|
2021-01-22 17:49:45 +00:00
|
|
|
|
2015-05-02 13:45:17 +00:00
|
|
|
"""
|
2014-03-04 12:11:04 +00:00
|
|
|
|
2021-01-22 17:49:45 +00:00
|
|
|
# pylint: disable=invalid-name, missing-function-docstring
|
|
|
|
|
|
|
|
import binascii
|
2021-06-18 09:49:20 +00:00
|
|
|
from datetime import datetime
|
2021-01-22 17:49:45 +00:00
|
|
|
import re
|
2020-08-06 15:42:46 +00:00
|
|
|
from urllib.parse import urlencode
|
2021-01-22 17:49:45 +00:00
|
|
|
from base64 import b64decode
|
2016-12-11 00:03:03 +00:00
|
|
|
from lxml import html
|
2021-01-22 17:49:45 +00:00
|
|
|
|
|
|
|
from searx import logger
|
|
|
|
from searx.utils import (
|
|
|
|
eval_xpath,
|
|
|
|
eval_xpath_list,
|
|
|
|
eval_xpath_getindex,
|
|
|
|
extract_text,
|
|
|
|
)
|
|
|
|
|
|
|
|
# pylint: disable=unused-import
|
|
|
|
from searx.engines.google import (
|
|
|
|
supported_languages_url,
|
|
|
|
_fetch_supported_languages,
|
|
|
|
)
|
|
|
|
# pylint: enable=unused-import
|
|
|
|
|
|
|
|
from searx.engines.google import (
|
2021-01-26 10:49:27 +00:00
|
|
|
get_lang_info,
|
|
|
|
detect_google_sorry,
|
2021-01-22 17:49:45 +00:00
|
|
|
)
|
2014-03-04 12:11:04 +00:00
|
|
|
|
2021-01-13 10:31:25 +00:00
|
|
|
# about
|
|
|
|
about = {
|
|
|
|
"website": 'https://news.google.com',
|
|
|
|
"wikidata_id": 'Q12020',
|
2021-01-26 10:49:27 +00:00
|
|
|
"official_api_documentation": 'https://developers.google.com/custom-search',
|
2021-01-13 10:31:25 +00:00
|
|
|
"use_official_api": False,
|
|
|
|
"require_api_key": False,
|
|
|
|
"results": 'HTML',
|
|
|
|
}
|
|
|
|
|
2021-01-22 17:49:45 +00:00
|
|
|
logger = logger.getChild('google news')
|
|
|
|
|
|
|
|
# compared to other google engines google-news has a different time range
|
|
|
|
# support. The time range is included in the search term.
|
|
|
|
time_range_dict = {
|
|
|
|
'day': 'when:1d',
|
|
|
|
'week': 'when:7d',
|
|
|
|
'month': 'when:1m',
|
|
|
|
'year': 'when:1y',
|
|
|
|
}
|
|
|
|
|
|
|
|
# engine dependent config
|
|
|
|
|
2014-03-04 12:11:04 +00:00
|
|
|
categories = ['news']
|
2021-01-22 17:49:45 +00:00
|
|
|
paging = False
|
|
|
|
use_locale_domain = True
|
2016-12-11 00:03:03 +00:00
|
|
|
time_range_support = True
|
2021-01-26 10:49:27 +00:00
|
|
|
|
|
|
|
# Google-News results are always *SafeSearch*. Option 'safesearch' is set to
|
|
|
|
# False here, otherwise checker will report safesearch-errors::
|
|
|
|
#
|
|
|
|
# safesearch : results are identitical for safesearch=0 and safesearch=2
|
|
|
|
safesearch = False
|
2014-03-04 12:11:04 +00:00
|
|
|
|
|
|
|
def request(query, params):
|
2021-01-22 17:49:45 +00:00
|
|
|
"""Google-News search request"""
|
|
|
|
|
2021-01-26 10:49:27 +00:00
|
|
|
lang_info = get_lang_info(
|
2021-01-22 17:49:45 +00:00
|
|
|
# pylint: disable=undefined-variable
|
2021-06-06 06:18:07 +00:00
|
|
|
params, supported_languages, language_aliases, False
|
2021-01-22 17:49:45 +00:00
|
|
|
)
|
2021-06-11 14:31:50 +00:00
|
|
|
logger.debug(
|
|
|
|
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
|
2021-01-22 17:49:45 +00:00
|
|
|
|
2021-01-26 10:49:27 +00:00
|
|
|
# google news has only one domain
|
|
|
|
lang_info['subdomain'] = 'news.google.com'
|
|
|
|
|
|
|
|
ceid = "%s:%s" % (lang_info['country'], lang_info['language'])
|
|
|
|
|
|
|
|
# google news redirects en to en-US
|
2021-06-18 09:34:11 +00:00
|
|
|
if lang_info['params']['hl'] == 'en':
|
|
|
|
lang_info['params']['hl'] = 'en-US'
|
2021-01-26 10:49:27 +00:00
|
|
|
|
|
|
|
# Very special to google-news compared to other google engines, the time
|
|
|
|
# range is included in the search term.
|
|
|
|
if params['time_range']:
|
2021-01-22 17:49:45 +00:00
|
|
|
query += ' ' + time_range_dict[params['time_range']]
|
|
|
|
|
2021-01-26 10:49:27 +00:00
|
|
|
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
|
2021-01-22 17:49:45 +00:00
|
|
|
'q': query,
|
2021-06-06 06:18:07 +00:00
|
|
|
**lang_info['params'],
|
2021-01-22 17:49:45 +00:00
|
|
|
'ie': "utf8",
|
|
|
|
'oe': "utf8",
|
2021-01-26 10:49:27 +00:00
|
|
|
'gl': lang_info['country'],
|
|
|
|
}) + ('&ceid=%s' % ceid) # ceid includes a ':' character which must not be urlencoded
|
|
|
|
params['url'] = query_url
|
2021-01-22 17:49:45 +00:00
|
|
|
|
2021-06-06 06:18:07 +00:00
|
|
|
params['headers'].update(lang_info['headers'])
|
2021-01-22 17:49:45 +00:00
|
|
|
params['headers']['Accept'] = (
|
|
|
|
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
|
|
|
|
)
|
2021-06-18 09:49:20 +00:00
|
|
|
params['headers']['Cookie'] = "CONSENT=YES+cb.%s-14-p0.en+F+941;" % datetime.now().strftime("%Y%m%d")
|
2021-01-24 07:53:35 +00:00
|
|
|
|
2014-03-04 12:11:04 +00:00
|
|
|
return params
|
|
|
|
|
|
|
|
|
|
|
|
def response(resp):
|
2021-01-22 17:49:45 +00:00
|
|
|
"""Get response from google's search request"""
|
2014-03-04 12:11:04 +00:00
|
|
|
results = []
|
2014-09-01 13:10:05 +00:00
|
|
|
|
2021-01-22 17:49:45 +00:00
|
|
|
detect_google_sorry(resp)
|
|
|
|
|
|
|
|
# convert the text to dom
|
2016-12-11 00:03:03 +00:00
|
|
|
dom = html.fromstring(resp.text)
|
2014-03-04 12:11:04 +00:00
|
|
|
|
2021-01-22 17:49:45 +00:00
|
|
|
for result in eval_xpath_list(dom, '//div[@class="xrnccd"]'):
|
|
|
|
|
|
|
|
# The first <a> tag in the <article> contains the link to the
|
|
|
|
# article The href attribute of the <a> is a google internal link,
|
|
|
|
# we can't use. The real link is hidden in the jslog attribute:
|
|
|
|
#
|
|
|
|
# <a ...
|
|
|
|
# jslog="95014; 4:https://www.cnn.com/.../index.html; track:click"
|
|
|
|
# href="./articles/CAIiENu3nGS...?hl=en-US&gl=US&ceid=US%3Aen"
|
|
|
|
# ... />
|
|
|
|
|
|
|
|
jslog = eval_xpath_getindex(result, './article/a/@jslog', 0)
|
|
|
|
url = re.findall('http[^;]*', jslog)
|
|
|
|
if url:
|
|
|
|
url = url[0]
|
|
|
|
else:
|
|
|
|
# The real URL is base64 encoded in the json attribute:
|
|
|
|
# jslog="95014; 5:W251bGwsbnVsbCxudW...giXQ==; track:click"
|
|
|
|
jslog = jslog.split(";")[1].split(':')[1].strip()
|
|
|
|
try:
|
|
|
|
padding = (4 -(len(jslog) % 4)) * "="
|
|
|
|
jslog = b64decode(jslog + padding)
|
|
|
|
except binascii.Error:
|
|
|
|
# URL cant be read, skip this result
|
|
|
|
continue
|
|
|
|
|
|
|
|
# now we have : b'[null, ... null,"https://www.cnn.com/.../index.html"]'
|
|
|
|
url = re.findall('http[^;"]*', str(jslog))[0]
|
|
|
|
|
|
|
|
# the first <h3> tag in the <article> contains the title of the link
|
|
|
|
title = extract_text(eval_xpath(result, './article/h3[1]'))
|
|
|
|
|
|
|
|
# the first <div> tag in the <article> contains the content of the link
|
|
|
|
content = extract_text(eval_xpath(result, './article/div[1]'))
|
|
|
|
|
|
|
|
# the second <div> tag contains origin publisher and the publishing date
|
|
|
|
|
|
|
|
pub_date = extract_text(eval_xpath(result, './article/div[2]//time'))
|
|
|
|
pub_origin = extract_text(eval_xpath(result, './article/div[2]//a'))
|
|
|
|
|
|
|
|
pub_info = []
|
|
|
|
if pub_origin:
|
|
|
|
pub_info.append(pub_origin)
|
|
|
|
if pub_date:
|
|
|
|
# The pub_date is mostly a string like 'yesertday', not a real
|
|
|
|
# timezone date or time. Therefore we can't use publishedDate.
|
|
|
|
pub_info.append(pub_date)
|
|
|
|
pub_info = ', '.join(pub_info)
|
|
|
|
if pub_info:
|
|
|
|
content = pub_info + ': ' + content
|
|
|
|
|
|
|
|
# The image URL is located in a preceding sibling <img> tag, e.g.:
|
|
|
|
# "https://lh3.googleusercontent.com/DjhQh7DMszk.....z=-p-h100-w100"
|
|
|
|
# These URL are long but not personalized (double checked via tor).
|
|
|
|
|
|
|
|
img_src = extract_text(result.xpath('preceding-sibling::a/figure/img/@src'))
|
|
|
|
|
|
|
|
results.append({
|
|
|
|
'url': url,
|
|
|
|
'title': title,
|
|
|
|
'content': content,
|
|
|
|
'img_src': img_src,
|
|
|
|
})
|
2014-09-01 13:10:05 +00:00
|
|
|
|
|
|
|
# return results
|
2014-03-04 12:11:04 +00:00
|
|
|
return results
|