whoogle-search/app/utils/routing_utils.py

90 lines
3.3 KiB
Python
Raw Normal View History

Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
from app.filter import Filter, get_first_link
from app.utils.session_utils import generate_user_keys
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
from app.request import gen_query
from bs4 import BeautifulSoup
from cryptography.fernet import Fernet, InvalidToken
from flask import g
from typing import Any, Tuple
class RoutingUtils:
def __init__(self, request, config, session, cookies_disabled=False):
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
self.request_params = request.args if request.method == 'GET' else request.form
self.user_agent = request.headers.get('User-Agent')
self.feeling_lucky = False
self.config = config
self.session = session
self.query = ''
self.cookies_disabled = cookies_disabled
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
self.search_type = self.request_params.get('tbm') if 'tbm' in self.request_params else ''
self.bang_operators = {
'!gh': 'https://github.com/search?q=',
'!ddg': 'https://duckduckgo.com/?q=',
'!w': 'https://wikipedia.com/wiki/',
'!so': 'https://stackoverflow.com/search?q=',
'!a': 'https://amazon.com/s?k=',
'!ebay': 'https://ebay.com/sch/i.html?_nkw=',
}
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
def __getitem__(self, name):
return getattr(self, name)
def __setitem__(self, name, value):
return setattr(self, name, value)
def __delitem__(self, name):
return delattr(self, name)
def __contains__(self, name):
return hasattr(self, name)
def new_search_query(self) -> str:
# Generate a new element key each time a new search is performed
self.session['fernet_keys']['element_key'] = generate_user_keys(
cookies_disabled=self.cookies_disabled)['element_key']
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
q = self.request_params.get('q')
if q is None or len(q) == 0:
return ''
else:
# Attempt to decrypt if this is an internal link
try:
q = Fernet(self.session['fernet_keys']['text_key']).decrypt(q.encode()).decode()
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
except InvalidToken:
pass
# Reset text key
self.session['fernet_keys']['text_key'] = generate_user_keys(
cookies_disabled=self.cookies_disabled)['text_key']
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
# Format depending on whether or not the query is a "feeling lucky" query
self.feeling_lucky = q.startswith('! ')
self.query = q[2:] if self.feeling_lucky else q
return self.query
def bang_operator(self) -> str:
print(self.query)
for operator, url in self.bang_operators.items():
if operator in self.query:
return url + self.query.replace(operator, '').strip()
return ''
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
def generate_response(self) -> Tuple[Any, int]:
mobile = 'Android' in self.user_agent or 'iPhone' in self.user_agent
content_filter = Filter(self.session['fernet_keys'], mobile=mobile, config=self.config)
Project refactor (#85) * Major refactor of requests and session management - Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request * Added ability to save/load configs by name - New PUT method for config allows changing config with specified name - New methods in js controller to handle loading/saving of configs * Result formatting and removal of unused elements - Fixed question section formatting from results page (added appropriate padding and made questions styled as italic) - Removed user agent display from main config settings * Minor change to button label * Fixed issue with "de-pickling" of flask session Having a gitignore-everything ("*") file within a flask session folder seems to cause a weird bug where the state of the app becomes unusable from continuously trying to prune files listed in the gitignore (and it can't prune '*'). * Switched to pickling saved configs * Updated ad/sponsored content filter and conf naming Configs are now named with a .conf extension to allow for easier manual cleanup/modification of named config files Sponsored content now removed by basic string matching of span content * Version bump to 0.2.0 * Fixed request.send return style
2020-06-02 21:54:47 +03:00
full_query = gen_query(self.query, self.request_params, self.config, content_filter.near)
get_body = g.user_request.send(query=full_query).text
# Produce cleanable html soup from response
html_soup = BeautifulSoup(content_filter.reskin(get_body), 'html.parser')
if self.feeling_lucky:
return get_first_link(html_soup), 1
else:
formatted_results = content_filter.clean(html_soup)
return formatted_results, content_filter.elements