searxng/searx/engines/google_videos.py

189 lines
5.5 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""This is the implementation of the google videos engine.
.. admonition:: Content-Security-Policy (CSP)
This engine needs to allow images from the `data URLs`_ (prefixed with the
``data:`` scheme)::
Header set Content-Security-Policy "img-src 'self' data: ;"
.. _data URLs:
https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URIs
2017-07-22 03:17:28 +00:00
"""
# pylint: disable=invalid-name
2019-01-04 14:48:22 +00:00
import re
from urllib.parse import urlencode
from lxml import html
from searx.utils import (
eval_xpath,
eval_xpath_list,
eval_xpath_getindex,
extract_text,
)
from searx.engines.google import (
get_lang_info,
time_range_dict,
filter_mapping,
results_xpath,
g_section_with_header,
title_xpath,
href_xpath,
content_xpath,
suggestion_xpath,
detect_google_sorry,
)
# pylint: disable=unused-import
from searx.engines.google import (
supported_languages_url
, _fetch_supported_languages
)
# pylint: enable=unused-import
2017-07-22 03:17:28 +00:00
# about
about = {
"website": 'https://www.google.com',
"wikidata_id": 'Q219885',
"official_api_documentation": 'https://developers.google.com/custom-search',
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
2017-07-22 03:17:28 +00:00
# engine dependent config
2017-07-22 03:17:28 +00:00
categories = ['videos']
paging = False
language_support = True
use_locale_domain = True
2017-07-22 03:17:28 +00:00
time_range_support = True
safesearch = True
2017-07-22 03:17:28 +00:00
RE_CACHE = {}
2017-07-22 03:17:28 +00:00
def _re(regexpr):
"""returns compiled regular expression"""
RE_CACHE[regexpr] = RE_CACHE.get(regexpr, re.compile(regexpr))
return RE_CACHE[regexpr]
2017-07-22 03:17:28 +00:00
def scrap_out_thumbs(dom):
"""Scrap out thumbnail data from <script> tags.
"""
ret_val = {}
thumb_name = 'vidthumb'
2017-07-22 03:17:28 +00:00
for script in eval_xpath_list(dom, '//script[contains(., "_setImagesSrc")]'):
_script = script.text
# var s='data:image/jpeg;base64, ...'
_imgdata = _re("s='([^']*)").findall( _script)
if not _imgdata:
continue
# var ii=['vidthumb4','vidthumb7']
for _vidthumb in _re(r"(%s\d+)" % thumb_name).findall(_script):
# At least the equal sign in the URL needs to be decoded
ret_val[_vidthumb] = _imgdata[0].replace(r"\x3d", "=")
# {google.ldidly=-1;google.ldi={"vidthumb8":"https://...
for script in eval_xpath_list(dom, '//script[contains(., "google.ldi={")]'):
_script = script.text
for key_val in _re(r'"%s\d+\":\"[^\"]*"' % thumb_name).findall( _script) :
match = _re(r'"(%s\d+)":"(.*)"' % thumb_name).search(key_val)
if match:
# At least the equal sign in the URL needs to be decoded
ret_val[match.group(1)] = match.group(2).replace(r"\u003d", "=")
2017-07-22 03:17:28 +00:00
logger.debug("found %s imgdata for: %s", thumb_name, ret_val.keys())
return ret_val
2017-07-22 03:17:28 +00:00
def request(query, params):
"""Google-Video search request"""
lang_info = get_lang_info(
params, supported_languages, language_aliases, False
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query,
'tbm': "vid",
**lang_info['params'],
'ie': "utf8",
'oe': "utf8",
})
if params['time_range'] in time_range_dict:
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
if params['safesearch']:
query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
params['url'] = query_url
params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
2017-07-22 03:17:28 +00:00
return params
def response(resp):
"""Get response from google's search request"""
2017-07-22 03:17:28 +00:00
results = []
detect_google_sorry(resp)
# convert the text to dom
2017-07-22 03:17:28 +00:00
dom = html.fromstring(resp.text)
vidthumb_imgdata = scrap_out_thumbs(dom)
2017-07-22 03:17:28 +00:00
# parse results
for result in eval_xpath_list(dom, results_xpath):
# google *sections*
if extract_text(eval_xpath(result, g_section_with_header)):
logger.debug("ingoring <g-section-with-header>")
continue
title = extract_text(eval_xpath_getindex(result, title_xpath, 0))
url = eval_xpath_getindex(result, href_xpath, 0)
c_node = eval_xpath_getindex(result, content_xpath, 0)
# <img id="vidthumb1" ...>
img_id = eval_xpath_getindex(c_node, './div[1]//a/g-img/img/@id', 0, default=None)
if img_id is None:
continue
img_src = vidthumb_imgdata.get(img_id, None)
if not img_src:
logger.error("no vidthumb imgdata for: %s" % img_id)
img_src = eval_xpath_getindex(c_node, './div[1]//a/g-img/img/@src', 0)
length = extract_text(eval_xpath(c_node, './/div[1]//a/div[3]'))
content = extract_text(eval_xpath(c_node, './/div[2]/span'))
pub_info = extract_text(eval_xpath(c_node, './/div[2]/div'))
results.append({
'url': url,
'title': title,
'content': content,
'length': length,
'author': pub_info,
'thumbnail': img_src,
'template': 'videos.html',
})
# parse suggestion
for suggestion in eval_xpath_list(dom, suggestion_xpath):
# append suggestion
results.append({'suggestion': extract_text(suggestion)})
2017-07-22 03:17:28 +00:00
return results