whoogle-search/app/filter.py

134 lines
4.7 KiB
Python

from bs4 import BeautifulSoup
import re
import urllib.parse as urlparse
from urllib.parse import parse_qs
SKIP_ARGS = ['ref_src', 'utm']
class Filter:
def __init__(self, mobile=False, config=None):
if config is None:
config = {}
self.near = config['near'] if 'near' in config else None
self.dark = config['dark'] if 'dark' in config else False
self.nojs = config['nojs'] if 'nojs' in config else False
self.mobile = mobile
def __getitem__(self, name):
return getattr(self, name)
def reskin(self, page):
# Aesthetic only re-skinning
page = page.replace('>G<', '>Sh<')
pattern = re.compile('4285f4|ea4335|fbcc05|34a853|fbbc05', re.IGNORECASE)
page = pattern.sub('685e79', page)
if self.dark:
page = page.replace('fff', '000').replace('202124', 'ddd').replace('1967D2', '3b85ea')
return page
def clean(self, soup):
def remove_ads():
main_divs = soup.find('div', {'id': 'main'})
if main_divs is None:
return
result_divs = main_divs.findAll('div', recursive=False)
# Only ads/sponsored content use classes in the list of result divs
ad_divs = [ad_div for ad_div in result_divs if 'class' in ad_div.attrs]
for div in ad_divs:
div.decompose()
def sync_images():
for img in soup.find_all('img'):
if img['src'].startswith('//'):
img['src'] = 'https:' + img['src']
img['src'] = '/tmp?image_url=' + img['src']
def update_styling():
# Remove unnecessary button(s)
for button in soup.find_all('button'):
button.decompose()
# Remove svg logos
for svg in soup.find_all('svg'):
svg.decompose()
# Update logo
logo = soup.find('a', {'class': 'l'})
if logo and self.mobile:
logo['style'] = 'display:flex; justify-content:center; align-items:center; color:#685e79; ' \
'font-size:18px; '
# Fix search bar length on mobile
try:
search_bar = soup.find('header').find('form').find('div')
search_bar['style'] = 'width: 100%;'
except AttributeError:
pass
# Set up dark mode if active
if self.dark:
soup.find('html')['style'] = 'scrollbar-color: #333 #111;'
for input_element in soup.findAll('input'):
input_element['style'] = 'color:#fff;'
def update_links():
# Replace hrefs with only the intended destination (no "utm" type tags)
for a in soup.find_all('a', href=True):
href = a['href']
if '/advanced_search' in href:
a.decompose()
continue
if 'url?q=' in href:
# Strip unneeded arguments
result_link = urlparse.urlparse(href)
result_link = parse_qs(result_link.query)['q'][0]
parsed_link = urlparse.urlparse(result_link)
link_args = parse_qs(parsed_link.query)
safe_args = {}
for arg in link_args.keys():
if arg in SKIP_ARGS:
continue
safe_args[arg] = link_args[arg]
# Remove original link query and replace with filtered args
result_link = result_link.replace(parsed_link.query, '')
if len(safe_args) > 1:
result_link = result_link + urlparse.urlencode(safe_args)
else:
result_link = result_link.replace('?', '')
a['href'] = result_link
# Add no-js option
if self.nojs:
nojs_link = soup.new_tag('a')
nojs_link['href'] = '/window?location=' + result_link
nojs_link['style'] = 'display:block;width:100%;'
nojs_link.string = 'NoJS Link: ' + nojs_link['href']
a.append(BeautifulSoup('<br><hr><br>', 'html.parser'))
a.append(nojs_link)
# Ensure no extra scripts passed through
try:
for script in soup('script'):
script.decompose()
soup.find('div', id='sfooter').decompose()
except Exception:
pass
remove_ads()
sync_images()
update_styling()
update_links()
return soup