Fix incorrect request type for image searches
Previously had hardcoded POST requests for all requests that didn't use the header template (which currently is only the image tab). Also refactored how the Filter class works. It now requires a valid Config model to be provided, which is then set up as a class var that the filtering functions can use as needed, rather than setting specific values from the config as individual values (which was confusing and sloppy). Fixes #561main
parent
1867e7ad01
commit
10a15e06e1
|
@ -1,3 +1,4 @@
|
||||||
|
from app.models.config import Config
|
||||||
from app.models.endpoint import Endpoint
|
from app.models.endpoint import Endpoint
|
||||||
from app.request import VALID_PARAMS, MAPS_URL
|
from app.request import VALID_PARAMS, MAPS_URL
|
||||||
from app.utils.misc import read_config_bool
|
from app.utils.misc import read_config_bool
|
||||||
|
@ -45,18 +46,8 @@ class Filter:
|
||||||
# type result (such as "people also asked", "related searches", etc)
|
# type result (such as "people also asked", "related searches", etc)
|
||||||
RESULT_CHILD_LIMIT = 7
|
RESULT_CHILD_LIMIT = 7
|
||||||
|
|
||||||
def __init__(self, user_key: str, mobile=False, config=None) -> None:
|
def __init__(self, user_key: str, config: Config, mobile=False) -> None:
|
||||||
if config is None:
|
self.config = config
|
||||||
config = {}
|
|
||||||
self.near = config['near'] if 'near' in config else ''
|
|
||||||
self.dark = config['dark'] if 'dark' in config else False
|
|
||||||
self.nojs = config['nojs'] if 'nojs' in config else False
|
|
||||||
self.new_tab = config['new_tab'] if 'new_tab' in config else False
|
|
||||||
self.alt_redirect = config['alts'] if 'alts' in config else False
|
|
||||||
self.block_title = (
|
|
||||||
config['block_title'] if 'block_title' in config else '')
|
|
||||||
self.block_url = (
|
|
||||||
config['block_url'] if 'block_url' in config else '')
|
|
||||||
self.mobile = mobile
|
self.mobile = mobile
|
||||||
self.user_key = user_key
|
self.user_key = user_key
|
||||||
self.main_divs = ResultSet('')
|
self.main_divs = ResultSet('')
|
||||||
|
@ -69,16 +60,6 @@ class Filter:
|
||||||
def elements(self):
|
def elements(self):
|
||||||
return self._elements
|
return self._elements
|
||||||
|
|
||||||
def reskin(self, page: str) -> str:
|
|
||||||
# Aesthetic only re-skinning
|
|
||||||
if self.dark:
|
|
||||||
page = page.replace(
|
|
||||||
'fff', '000').replace(
|
|
||||||
'202124', 'ddd').replace(
|
|
||||||
'1967D2', '3b85ea')
|
|
||||||
|
|
||||||
return page
|
|
||||||
|
|
||||||
def encrypt_path(self, path, is_element=False) -> str:
|
def encrypt_path(self, path, is_element=False) -> str:
|
||||||
# Encrypts path to avoid plaintext results in logs
|
# Encrypts path to avoid plaintext results in logs
|
||||||
if is_element:
|
if is_element:
|
||||||
|
@ -109,7 +90,7 @@ class Filter:
|
||||||
|
|
||||||
input_form = soup.find('form')
|
input_form = soup.find('form')
|
||||||
if input_form is not None:
|
if input_form is not None:
|
||||||
input_form['method'] = 'POST'
|
input_form['method'] = 'GET' if self.config.get_only else 'POST'
|
||||||
|
|
||||||
# Ensure no extra scripts passed through
|
# Ensure no extra scripts passed through
|
||||||
for script in soup('script'):
|
for script in soup('script'):
|
||||||
|
@ -143,9 +124,7 @@ class Filter:
|
||||||
_ = div.decompose() if len(div_ads) else None
|
_ = div.decompose() if len(div_ads) else None
|
||||||
|
|
||||||
def remove_block_titles(self) -> None:
|
def remove_block_titles(self) -> None:
|
||||||
if not self.main_divs:
|
if not self.main_divs or not self.config.block_title:
|
||||||
return
|
|
||||||
if self.block_title == '':
|
|
||||||
return
|
return
|
||||||
block_title = re.compile(self.block_title)
|
block_title = re.compile(self.block_title)
|
||||||
for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]:
|
for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]:
|
||||||
|
@ -154,9 +133,7 @@ class Filter:
|
||||||
_ = div.decompose() if len(block_divs) else None
|
_ = div.decompose() if len(block_divs) else None
|
||||||
|
|
||||||
def remove_block_url(self) -> None:
|
def remove_block_url(self) -> None:
|
||||||
if not self.main_divs:
|
if not self.main_divs or not self.config.block_url:
|
||||||
return
|
|
||||||
if self.block_url == '':
|
|
||||||
return
|
return
|
||||||
block_url = re.compile(self.block_url)
|
block_url = re.compile(self.block_url)
|
||||||
for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]:
|
for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]:
|
||||||
|
@ -244,7 +221,7 @@ class Filter:
|
||||||
if src.startswith(LOGO_URL):
|
if src.startswith(LOGO_URL):
|
||||||
# Re-brand with Whoogle logo
|
# Re-brand with Whoogle logo
|
||||||
element.replace_with(BeautifulSoup(
|
element.replace_with(BeautifulSoup(
|
||||||
render_template('logo.html', dark=self.dark),
|
render_template('logo.html'),
|
||||||
features='html.parser'))
|
features='html.parser'))
|
||||||
return
|
return
|
||||||
elif src.startswith(GOOG_IMG) or GOOG_STATIC in src:
|
elif src.startswith(GOOG_IMG) or GOOG_STATIC in src:
|
||||||
|
@ -323,10 +300,10 @@ class Filter:
|
||||||
link['href'] = filter_link_args(q)
|
link['href'] = filter_link_args(q)
|
||||||
|
|
||||||
# Add no-js option
|
# Add no-js option
|
||||||
if self.nojs:
|
if self.config.nojs:
|
||||||
append_nojs(link)
|
append_nojs(link)
|
||||||
|
|
||||||
if self.new_tab:
|
if self.config.new_tab:
|
||||||
link['target'] = '_blank'
|
link['target'] = '_blank'
|
||||||
else:
|
else:
|
||||||
if href.startswith(MAPS_URL):
|
if href.startswith(MAPS_URL):
|
||||||
|
@ -336,7 +313,7 @@ class Filter:
|
||||||
link['href'] = href
|
link['href'] = href
|
||||||
|
|
||||||
# Replace link location if "alts" config is enabled
|
# Replace link location if "alts" config is enabled
|
||||||
if self.alt_redirect:
|
if self.config.alts:
|
||||||
# Search and replace all link descriptions
|
# Search and replace all link descriptions
|
||||||
# with alternative location
|
# with alternative location
|
||||||
link['href'] = get_site_alt(link['href'])
|
link['href'] = get_site_alt(link['href'])
|
||||||
|
|
|
@ -59,7 +59,7 @@ def gen_user_agent(is_mobile) -> str:
|
||||||
return DESKTOP_UA.format("Mozilla", linux, firefox)
|
return DESKTOP_UA.format("Mozilla", linux, firefox)
|
||||||
|
|
||||||
|
|
||||||
def gen_query(query, args, config, near_city=None) -> str:
|
def gen_query(query, args, config) -> str:
|
||||||
param_dict = {key: '' for key in VALID_PARAMS}
|
param_dict = {key: '' for key in VALID_PARAMS}
|
||||||
|
|
||||||
# Use :past(hour/day/week/month/year) if available
|
# Use :past(hour/day/week/month/year) if available
|
||||||
|
@ -96,8 +96,8 @@ def gen_query(query, args, config, near_city=None) -> str:
|
||||||
param_dict['start'] = '&start=' + args.get('start')
|
param_dict['start'] = '&start=' + args.get('start')
|
||||||
|
|
||||||
# Search for results near a particular city, if available
|
# Search for results near a particular city, if available
|
||||||
if near_city:
|
if config.near:
|
||||||
param_dict['near'] = '&near=' + urlparse.quote(near_city)
|
param_dict['near'] = '&near=' + urlparse.quote(config.near)
|
||||||
|
|
||||||
# Set language for results (lr) if source isn't set, otherwise use the
|
# Set language for results (lr) if source isn't set, otherwise use the
|
||||||
# result language param provided in the results
|
# result language param provided in the results
|
||||||
|
|
|
@ -119,8 +119,7 @@ class Search:
|
||||||
config=self.config)
|
config=self.config)
|
||||||
full_query = gen_query(self.query,
|
full_query = gen_query(self.query,
|
||||||
self.request_params,
|
self.request_params,
|
||||||
self.config,
|
self.config)
|
||||||
content_filter.near)
|
|
||||||
|
|
||||||
# force mobile search when view image is true and
|
# force mobile search when view image is true and
|
||||||
# the request is not already made by a mobile
|
# the request is not already made by a mobile
|
||||||
|
@ -132,7 +131,7 @@ class Search:
|
||||||
force_mobile=view_image)
|
force_mobile=view_image)
|
||||||
|
|
||||||
# Produce cleanable html soup from response
|
# Produce cleanable html soup from response
|
||||||
html_soup = bsoup(content_filter.reskin(get_body.text), 'html.parser')
|
html_soup = bsoup(get_body.text, 'html.parser')
|
||||||
|
|
||||||
# Replace current soup if view_image is active
|
# Replace current soup if view_image is active
|
||||||
if view_image:
|
if view_image:
|
||||||
|
|
|
@ -1,5 +1,6 @@
|
||||||
from bs4 import BeautifulSoup
|
from bs4 import BeautifulSoup
|
||||||
from app.filter import Filter
|
from app.filter import Filter
|
||||||
|
from app.models.config import Config
|
||||||
from app.models.endpoint import Endpoint
|
from app.models.endpoint import Endpoint
|
||||||
from app.utils.session import generate_user_key
|
from app.utils.session import generate_user_key
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
|
@ -11,7 +12,7 @@ from test.conftest import demo_config
|
||||||
|
|
||||||
def get_search_results(data):
|
def get_search_results(data):
|
||||||
secret_key = generate_user_key()
|
secret_key = generate_user_key()
|
||||||
soup = Filter(user_key=secret_key).clean(
|
soup = Filter(user_key=secret_key, config=Config(**demo_config)).clean(
|
||||||
BeautifulSoup(data, 'html.parser'))
|
BeautifulSoup(data, 'html.parser'))
|
||||||
|
|
||||||
main_divs = soup.find('div', {'id': 'main'})
|
main_divs = soup.find('div', {'id': 'main'})
|
||||||
|
@ -74,7 +75,7 @@ def test_block_results(client):
|
||||||
|
|
||||||
assert has_pinterest
|
assert has_pinterest
|
||||||
|
|
||||||
demo_config['block'] = 'pinterest.com'
|
demo_config['block'] = 'pinterest.com,help.pinterest.com'
|
||||||
rv = client.post(f'/{Endpoint.config}', data=demo_config)
|
rv = client.post(f'/{Endpoint.config}', data=demo_config)
|
||||||
assert rv._status_code == 302
|
assert rv._status_code == 302
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue