Merge pull request #2 from benbusby/main

Implement changes from upstream

Dockerfile

@@ -15,10 +15,17 @@ RUN pip install --prefix /install --no-warn-script-location --no-cache-dir -r re
 FROM python:3.11.0a5-alpine
 
 RUN apk add --update --no-cache tor curl openrc libstdc++
+# git go //for obfs4proxy
 # libcurl4-openssl-dev
 
 RUN apk -U upgrade
 
+# uncomment to build obfs4proxy
+# RUN git clone https://gitlab.com/yawning/obfs4.git
+# WORKDIR /obfs4
+# RUN go build -o obfs4proxy/obfs4proxy ./obfs4proxy
+# RUN cp ./obfs4proxy/obfs4proxy /usr/bin/obfs4proxy
+
 ARG DOCKER_USER=whoogle
 ARG DOCKER_USERID=927
 ARG config_dir=/config

README.md

@@ -102,7 +102,7 @@ ___
 
 ### [Fly.io](https://fly.io)
 
-You will need a **PAID** [Fly.io](https://fly.io) account to deploy Whoogle.
+You will need a [Fly.io](https://fly.io) account to deploy Whoogle. The [free allowances](https://fly.io/docs/about/pricing/#free-allowances) are enough for personal use.
 
 #### Install the CLI: https://fly.io/docs/hands-on/installing/
 
@@ -234,6 +234,7 @@ ExecStart=<python_install_dir>/python3 <whoogle_install_dir>/whoogle-search --ho
 ExecStart=<whoogle_repo_dir>/run
 # For example:
 # ExecStart=/var/www/whoogle-search/run
+WorkingDirectory=<whoogle_repo_dir>
 ExecReload=/bin/kill -HUP $MAINPID
 Restart=always
 RestartSec=3
@@ -446,6 +447,7 @@ These environment variables allow setting default config values, but can be over
 | WHOOGLE_CONFIG_STYLE                 | The custom CSS to use for styling (should be single line)       |
 | WHOOGLE_CONFIG_PREFERENCES_ENCRYPTED | Encrypt preferences token, requires preferences key             |
 | WHOOGLE_CONFIG_PREFERENCES_KEY       | Key to encrypt preferences in URL (REQUIRED to show url)        |
+| WHOOGLE_CONFIG_ANON_VIEW             | Include the "anonymous view" option for each search result      |
 
 ## Usage
 Same as most search engines, with the exception of filtering by time range.
@@ -654,7 +656,7 @@ A lot of the app currently piggybacks on Google's existing support for fetching
 | [https://search.sethforprivacy.com](https://search.sethforprivacy.com) | 🇩🇪 DE | English | |
 | [https://whoogle.dcs0.hu](https://whoogle.dcs0.hu) | 🇭🇺 HU | Multi-choice | |
 | [https://gowogle.voring.me](https://gowogle.voring.me) | 🇺🇸 US | Multi-choice | |
-| [https://whoogle.privacydev.net](https://whoogle.privacydev.net) | 🇩🇪 DE | English | |
+| [https://whoogle.privacydev.net](https://whoogle.privacydev.net) | 🇫🇷 FR | English | |
 | [https://wg.vern.cc](https://wg.vern.cc) | 🇺🇸 US | English |  |
 | [https://whoogle.hxvy0.gq](https://whoogle.hxvy0.gq) | 🇨🇦 CA | Turkish Only | ✅ |
 | [https://whoogle.hostux.net](https://whoogle.hostux.net) | 🇫🇷 FR | Multi-choice | |
@@ -664,6 +666,9 @@ A lot of the app currently piggybacks on Google's existing support for fetching
 | [https://search.rubberverse.xyz](https://search.rubberverse.xyz) | 🇵🇱 PL | English | |
 | [https://whoogle.ftw.lol](https://whoogle.ftw.lol) | 🇩🇪 DE | Multi-choice | |
 | [https://whoogle-search--replitcomreside.repl.co](https://whoogle-search--replitcomreside.repl.co) | 🇺🇸 US | English |  |
+| [https://search.notrustverify.ch](https://search.notrustverify.ch) | 🇨🇭 CH | Multi-choice |  |
+| [https://whoogle.datura.network](https://whoogle.datura.network) | 🇩🇪 DE | Multi-choice | |
+| [https://whoogle.yepserver.xyz](https://whoogle.yepserver.xyz) | 🇺🇦 UA | Multi-choice | |
 
 
 * A checkmark in the "Cloudflare" category here refers to the use of the reverse proxy, [Cloudflare](https://cloudflare.com). The checkmark will not be listed for a site which uses Cloudflare DNS but rather the proxying service which grants Cloudflare the ability to monitor traffic to the website.
@@ -675,7 +680,8 @@ A lot of the app currently piggybacks on Google's existing support for fetching
 | [http://whoglqjdkgt2an4tdepberwqz3hk7tjo4kqgdnuj77rt7nshw2xqhqad.onion](http://whoglqjdkgt2an4tdepberwqz3hk7tjo4kqgdnuj77rt7nshw2xqhqad.onion) | 🇺🇸 US |  Multi-choice
 | [http://nuifgsnbb2mcyza74o7illtqmuaqbwu4flam3cdmsrnudwcmkqur37qd.onion](http://nuifgsnbb2mcyza74o7illtqmuaqbwu4flam3cdmsrnudwcmkqur37qd.onion) | 🇩🇪 DE |  English
 | [http://whoogle.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad.onion](http://whoogle.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad.onion/) | 🇺🇸 US | English |
-| [http://whoogle.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid.onion](http://whoogle.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid.onion/) | 🇩🇪 DE | English |
+| [http://whoogle.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid.onion](http://whoogle.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid.onion/) | 🇫🇷 FR | English |
+| [http://whoogle.daturab6drmkhyeia4ch5gvfc2f3wgo6bhjrv3pz6n7kxmvoznlkq4yd.onion](http://whoogle.daturab6drmkhyeia4ch5gvfc2f3wgo6bhjrv3pz6n7kxmvoznlkq4yd.onion/) | 🇩🇪 DE | Multi-choice | |
 
 #### I2P Instances
 

app/filter.py

@@ -3,6 +3,7 @@ from bs4 import BeautifulSoup
 from bs4.element import ResultSet, Tag
 from cryptography.fernet import Fernet
 from flask import render_template
+import html
 import urllib.parse as urlparse
 from urllib.parse import parse_qs
 import re
@@ -44,7 +45,7 @@ def extract_q(q_str: str, href: str) -> str:
     Returns:
         str: The 'q' element of the link, or an empty string
     """
-    return parse_qs(q_str)['q'][0] if ('&q=' in href or '?q=' in href) else ''
+    return parse_qs(q_str, keep_blank_values=True)['q'][0] if ('&q=' in href or '?q=' in href) else ''
 
 
 def build_map_url(href: str) -> str:
@@ -160,14 +161,22 @@ class Filter:
         self.update_styling()
         self.remove_block_tabs()
 
+        # self.main_divs is only populated for the main page of search results
+        # (i.e. not images/news/etc).
+        if self.main_divs:
+            for div in self.main_divs:
+                self.sanitize_div(div)
+
         for img in [_ for _ in self.soup.find_all('img') if 'src' in _.attrs]:
             self.update_element_src(img, 'image/png')
 
         for audio in [_ for _ in self.soup.find_all('audio') if 'src' in _.attrs]:
             self.update_element_src(audio, 'audio/mpeg')
+            audio['controls'] = ''
 
         for link in self.soup.find_all('a', href=True):
             self.update_link(link)
+            self.add_favicon(link)
 
         if self.config.alts:
             self.site_alt_swap()
@@ -201,6 +210,85 @@ class Filter:
         self.remove_site_blocks(self.soup)
         return self.soup
 
+    def sanitize_div(self, div) -> None:
+        """Removes escaped script and iframe tags from results
+
+        Returns:
+            None (The soup object is modified directly)
+        """
+        if not div:
+            return
+
+        for d in div.find_all('div', recursive=True):
+            d_text = d.find(text=True, recursive=False)
+
+            # Ensure we're working with tags that contain text content
+            if not d_text or not d.string:
+                continue
+
+            d.string = html.unescape(d_text)
+            div_soup = BeautifulSoup(d.string, 'html.parser')
+
+            # Remove all valid script or iframe tags in the div
+            for script in div_soup.find_all('script'):
+                script.decompose()
+
+            for iframe in div_soup.find_all('iframe'):
+                iframe.decompose()
+
+            d.string = str(div_soup)
+
+    def add_favicon(self, link) -> None:
+        """Adds icons for each returned result, using the result site's favicon
+
+        Returns:
+            None (The soup object is modified directly)
+        """
+        # Skip empty, parentless, or internal links
+        if not link or not link.parent or not link['href'].startswith('http'):
+            return
+
+        parent = link.parent
+        is_result_div = False
+
+        # Check each parent to make sure that the div doesn't already have a
+        # favicon attached, and that the div is a result div
+        while parent:
+            p_cls = parent.attrs.get('class') or []
+            if 'has-favicon' in p_cls or GClasses.scroller_class in p_cls:
+                return
+            elif GClasses.result_class_a not in p_cls:
+                parent = parent.parent
+            else:
+                is_result_div = True
+                break
+
+        if not is_result_div:
+            return
+
+        # Construct the html for inserting the icon into the parent div
+        parsed = urlparse.urlparse(link['href'])
+        favicon = self.encrypt_path(
+            f'{parsed.scheme}://{parsed.netloc}/favicon.ico',
+            is_element=True)
+        src = f'{self.root_url}/{Endpoint.element}?url={favicon}' + \
+            '&type=image/x-icon'
+        html = f'<img class="site-favicon" src="{src}">'
+
+        favicon = BeautifulSoup(html, 'html.parser')
+        link.parent.insert(0, favicon)
+
+        # Update all parents to indicate that a favicon has been attached
+        parent = link.parent
+        while parent:
+            p_cls = parent.get('class') or []
+            p_cls.append('has-favicon')
+            parent['class'] = p_cls
+            parent = parent.parent
+
+            if GClasses.result_class_a in p_cls:
+                break
+
     def remove_site_blocks(self, soup) -> None:
         if not self.config.block or not soup.body:
             return

app/models/g_classes.py

@@ -14,6 +14,7 @@ class GClasses:
     footer = 'TuS8Ad'
     result_class_a = 'ZINbbc'
     result_class_b = 'luh4td'
+    scroller_class = 'idg8be'
 
     result_classes = {
         result_class_a: ['Gx5Zad'],

app/request.py

@@ -307,9 +307,8 @@ class Request:
         # view is suppressed correctly
         now = datetime.now()
         cookies = {
-            'CONSENT': 'YES+cb.{:d}{:02d}{:02d}-17-p0.de+F+678'.format(
+            'CONSENT': 'PENDING+987',
-                now.year, now.month, now.day
+            'SOCS': 'CAESHAgBEhIaAB', 
-            )
         }
 
         # Validate Tor conn and request new identity if the last one failed

app/routes.py

@@ -4,8 +4,10 @@ import io
 import json
 import os
 import pickle
+import re
 import urllib.parse as urlparse
 import uuid
+import validators
 from datetime import datetime, timedelta
 from functools import wraps
 
@@ -15,10 +17,11 @@ from app.models.config import Config
 from app.models.endpoint import Endpoint
 from app.request import Request, TorError
 from app.utils.bangs import resolve_bang
-from app.utils.misc import get_proxy_host_url
+from app.utils.misc import empty_gif, placeholder_img, get_proxy_host_url, \
+    fetch_favicon
 from app.filter import Filter
 from app.utils.misc import read_config_bool, get_client_ip, get_request_url, \
-    check_for_update
+    check_for_update, encrypt_string
 from app.utils.widgets import *
 from app.utils.results import bold_search_terms,\
     add_currency_card, check_currency, get_tabs_content
@@ -31,6 +34,7 @@ from requests import exceptions
 from requests.models import PreparedRequest
 from cryptography.fernet import Fernet, InvalidToken
 from cryptography.exceptions import InvalidSignature
+from werkzeug.datastructures import MultiDict
 
 # Load DDG bang json files only on init
 bang_json = json.load(open(app.config['BANG_FILE'])) or {}
@@ -181,6 +185,7 @@ def before_request_func():
 def after_request_func(resp):
     resp.headers['X-Content-Type-Options'] = 'nosniff'
     resp.headers['X-Frame-Options'] = 'DENY'
+    resp.headers['Cache-Control'] = 'max-age=86400'
 
     if os.getenv('WHOOGLE_CSP', False):
         resp.headers['Content-Security-Policy'] = app.config['CSP']
@@ -298,6 +303,13 @@ def autocomplete():
 @session_required
 @auth_required
 def search():
+    if request.method == 'POST':
+        # Redirect as a GET request with an encrypted query
+        post_data = MultiDict(request.form)
+        post_data['q'] = encrypt_string(g.session_key, post_data['q'])
+        get_req_str = urlparse.urlencode(post_data)
+        return redirect(url_for('.search') + '?' + get_req_str)
+
     search_util = Search(request, g.user_config, g.session_key)
     query = search_util.new_search_query()
 
@@ -420,13 +432,18 @@ def config():
     config_disabled = (
             app.config['CONFIG_DISABLE'] or
             not valid_user_session(session))
+
+    name = ''
+    if 'name' in request.args:
+        name = os.path.normpath(request.args.get('name'))
+        if not re.match(r'^[A-Za-z0-9_.+-]+$', name):
+            return make_response('Invalid config name', 400)
+
     if request.method == 'GET':
         return json.dumps(g.user_config.__dict__)
     elif request.method == 'PUT' and not config_disabled:
-        if 'name' in request.args:
+        if name:
-            config_pkl = os.path.join(
+            config_pkl = os.path.join(app.config['CONFIG_PATH'], name)
-                app.config['CONFIG_PATH'],
-                request.args.get('name'))
             session['config'] = (pickle.load(open(config_pkl, 'rb'))
                                  if os.path.exists(config_pkl)
                                  else session['config'])
@@ -444,7 +461,7 @@ def config():
                 config_data,
                 open(os.path.join(
                     app.config['CONFIG_PATH'],
-                    request.args.get('name')), 'wb'))
+                    name), 'wb'))
 
         session['config'] = config_data
         return redirect(config_data['url'])
@@ -475,8 +492,23 @@ def element():
 
     src_type = request.args.get('type')
 
+    # Ensure requested element is from a valid domain
+    domain = urlparse.urlparse(src_url).netloc
+    if not validators.domain(domain):
+        return send_file(io.BytesIO(empty_gif), mimetype='image/gif')
+
     try:
-        file_data = g.user_request.send(base_url=src_url).content
+        response = g.user_request.send(base_url=src_url)
+
+        # Display an empty gif if the requested element couldn't be retrieved
+        if response.status_code != 200 or len(response.content) == 0:
+            if 'favicon' in src_url:
+                favicon = fetch_favicon(src_url)
+                return send_file(io.BytesIO(favicon), mimetype='image/png')
+            else:
+                return send_file(io.BytesIO(empty_gif), mimetype='image/gif')
+
+        file_data = response.content
         tmp_mem = io.BytesIO()
         tmp_mem.write(file_data)
         tmp_mem.seek(0)
@@ -485,8 +517,6 @@ def element():
     except exceptions.RequestException:
         pass
 
-    empty_gif = base64.b64decode(
-        'R0lGODlhAQABAIAAAP///////yH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==')
     return send_file(io.BytesIO(empty_gif), mimetype='image/gif')
 
 
@@ -504,6 +534,13 @@ def window():
         root_url=request.url_root,
         config=g.user_config)
     target = urlparse.urlparse(target_url)
+
+    # Ensure requested URL has a valid domain
+    if not validators.domain(target.netloc):
+        return render_template(
+            'error.html',
+            error_message='Invalid location'), 400
+
     host_url = f'{target.scheme}://{target.netloc}'
 
     get_body = g.user_request.send(base_url=target_url).text

app/static/css/search.css

@@ -65,6 +65,26 @@ details summary span {
     text-align: center;
 }
 
+.site-favicon {
+	float: left;
+	width: 25px;
+	padding-right: 5px;
+}
+
+.sCuL3 {
+	padding-left: 30px;
+}
+
+#flex_text_audio_icon_chunk {
+	display: none;
+}
+
+audio {
+	display: block;
+	margin-right: auto;
+	padding-bottom: 5px;
+}
+
 @media (min-width: 801px) {
     body {
         min-width: 736px !important;

app/static/settings/header_tabs.json

@@ -13,7 +13,7 @@
   },
   "maps": {
       "tbm": null,
-      "href": "https://maps.google.com/maps?q={query}",
+      "href": "https://maps.google.com/maps?q={map_query}",
       "name": "Maps",
       "selected": false
   },

app/utils/misc.py

@@ -1,11 +1,52 @@
+import base64
 from bs4 import BeautifulSoup as bsoup
+from cryptography.fernet import Fernet
 from flask import Request
 import hashlib
+import io
 import os
 import re
 from requests import exceptions, get
 from urllib.parse import urlparse
 
+ddg_favicon_site = 'http://icons.duckduckgo.com/ip2'
+
+empty_gif = base64.b64decode(
+    'R0lGODlhAQABAIAAAP///////yH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==')
+
+placeholder_img = base64.b64decode(
+    'iVBORw0KGgoAAAANSUhEUgAAABkAAAAZCAYAAADE6YVjAAABF0lEQVRIS8XWPw9EMBQA8Eok' \
+    'JBKrMFqMBt//GzAYLTZ/VomExPDu6uLiaPteqVynBn0/75W2Vp7nEIYhe6p1XcespmmAd7Is' \
+    'M+4URcGiKPogvMMvmIS2eN9MOMKbKWgf54SYgI4vKkTuQKJKSJErkKzUSkQHUs0lilAg7GMh' \
+    'ISoIA/hYMiKCKIA2soeowCWEMkfHtUmrXLcyGYYBfN9HF8djiaglWzNZlgVs21YisoAUaEXG' \
+    'cQTP86QIFgi7vyLzPIPjOEIEC7ANQv/4aZrAdd0TUtc1i+MYnSsMWjPp+x6CIPgJVlUVS5KE' \
+    'DKig/+wnVzM4pnzaGeHd+ENlWbI0TbVLJBtw2uMfP63wc9d2kDCWxi5Q27bsBerSJ9afJbeL' \
+    'AAAAAElFTkSuQmCC'
+)
+
+
+def fetch_favicon(url: str) -> bytes:
+    """Fetches a favicon using DuckDuckGo's favicon retriever
+
+    Args:
+        url: The url to fetch the favicon from
+    Returns:
+        bytes - the favicon bytes, or a placeholder image if one
+        was not returned
+    """
+    domain = urlparse(url).netloc
+
+    response = get(f'{ddg_favicon_site}/{domain}.ico')
+
+    if response.status_code == 200 and len(response.content) > 0:
+        tmp_mem = io.BytesIO()
+        tmp_mem.write(response.content)
+        tmp_mem.seek(0)
+
+        return tmp_mem.read()
+    else:
+        return placeholder_img
+
 
 def gen_file_hash(path: str, static_file: str) -> str:
     file_contents = open(os.path.join(path, static_file), 'rb').read()
@@ -86,3 +127,13 @@ def list_to_dict(lst: list) -> dict:
         return {}
     return {lst[i].replace(' ', ''): lst[i+1].replace(' ', '')
             for i in range(0, len(lst), 2)}
+
+
+def encrypt_string(key: bytes, string: str) -> str:
+    cipher_suite = Fernet(key)
+    return cipher_suite.encrypt(string.encode()).decode()
+
+
+def decrypt_string(key: bytes, string: str) -> str:
+    cipher_suite = Fernet(g.session_key)
+    return cipher_suite.decrypt(string.encode()).decode()

app/utils/results.py

@@ -418,6 +418,10 @@ def get_tabs_content(tabs: dict,
     Returns:
         dict: contains the name, the href and if the tab is selected or not
     """
+    map_query = full_query
+    if '-site:' in full_query:
+        block_idx = full_query.index('-site:')
+        map_query = map_query[:block_idx]
     tabs = copy.deepcopy(tabs)
     for tab_id, tab_content in tabs.items():
         # update name to desired language
@@ -433,7 +437,9 @@ def get_tabs_content(tabs: dict,
         if preferences:
             query = f"{query}&preferences={preferences}"
 
-        tab_content['href'] = tab_content['href'].format(query=query)
+        tab_content['href'] = tab_content['href'].format(
+            query=query,
+            map_query=map_query)
 
         # update if selected tab (default all tab is selected)
         if tab_content['tbm'] == search_type:

app/utils/search.py

@@ -109,7 +109,9 @@ class Search:
         self.widget = "ip" if re.search("([^a-z0-9]|^)my *[^a-z0-9] *(ip|internet protocol)" +
                         "($|( *[^a-z0-9] *(((addres|address|adres|" +
                         "adress)|a)? *$)))", self.query.lower()) else self.widget
-        self.widget = 'calculator' if re.search("calculator|calc|calclator|math", self.query.lower()) else self.widget
+        self.widget = 'calculator' if re.search(
+                r"\bcalculator\b|\bcalc\b|\bcalclator\b|\bmath\b",
+                self.query.lower()) else self.widget
         return self.query
 
     def generate_response(self) -> str:

app/utils/widgets.py

@@ -1,5 +1,10 @@
+from pathlib import Path
 from bs4 import BeautifulSoup
 
+
+# root
+BASE_DIR = Path(__file__).parent.parent.parent
+
 def add_ip_card(html_soup: BeautifulSoup, ip: str) -> BeautifulSoup:
     """Adds the client's IP address to the search results
         if query contains keywords
@@ -48,7 +53,8 @@ def add_calculator_card(html_soup: BeautifulSoup) -> BeautifulSoup:
     """
     main_div = html_soup.select_one('#main')
     if main_div:
-        widget_file = open('app/static/widgets/calculator.html')
+        # absolute path
+        widget_file = open(BASE_DIR / 'app/static/widgets/calculator.html', encoding="utf8")
         widget_tag = html_soup.new_tag('div')
         widget_tag['class'] = 'ZINbbc xpd O9g5cc uUPGi'
         widget_tag['id'] = 'calculator-wrapper'
@@ -56,7 +62,7 @@ def add_calculator_card(html_soup: BeautifulSoup) -> BeautifulSoup:
         calculator_text['class'] = 'kCrYT ip-address-div'
         calculator_text.string = 'Calculator'
         calculator_widget = html_soup.new_tag('div')
-        calculator_widget.append(BeautifulSoup(widget_file, 'html.parser'));
+        calculator_widget.append(BeautifulSoup(widget_file, 'html.parser'))
         calculator_widget['class'] = 'kCrYT ip-text-div'
         widget_tag.append(calculator_text)
         widget_tag.append(calculator_widget)

app/version.py

@@ -4,4 +4,4 @@ optional_dev_tag = ''
 if os.getenv('DEV_BUILD'):
     optional_dev_tag = '.dev' + os.getenv('DEV_BUILD')
 
-__version__ = '0.8.2' + optional_dev_tag
+__version__ = '0.8.3' + optional_dev_tag

charts/whoogle/Chart.yaml

@@ -3,7 +3,7 @@ name: whoogle
 description: A self hosted search engine on Kubernetes
 type: application
 version: 0.1.0
-appVersion: 0.8.2
+appVersion: 0.8.3
 
 icon: https://github.com/benbusby/whoogle-search/raw/main/app/static/img/favicon/favicon-96x96.png
 

charts/whoogle/templates/deployment.yaml

@@ -52,10 +52,20 @@ spec:
             httpGet:
               path: /
               port: http
+              {{- if and .Values.conf.WHOOGLE_USER .Values.conf.WHOOGLE_PASS }}
+              httpHeaders:
+                - name: Authorization
+                  value: Basic {{ b64enc (printf "%s:%s" .Values.conf.WHOOGLE_USER .Values.conf.WHOOGLE_PASS) }}
+              {{- end }}
           readinessProbe:
             httpGet:
               path: /
               port: http
+              {{- if and .Values.conf.WHOOGLE_USER .Values.conf.WHOOGLE_PASS }}
+              httpHeaders:
+                - name: Authorization
+                  value: Basic {{ b64enc (printf "%s:%s" .Values.conf.WHOOGLE_USER .Values.conf.WHOOGLE_PASS) }}
+              {{- end }}
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
       {{- with .Values.nodeSelector }}

misc/instances.txt

@@ -18,3 +18,6 @@ https://whoogle.no-logs.com
 https://search.rubberverse.xyz
 https://whoogle.ftw.lol
 https://whoogle-search--replitcomreside.repl.co
+https://search.notrustverify.ch
+https://whoogle.datura.network
+https://whoogle.yepserver.xyz

misc/tor/torrc

@@ -7,3 +7,6 @@ ExtORPortCookieAuthFileGroupReadable 1
 CacheDirectoryGroupReadable 1
 CookieAuthFile /var/lib/tor/control_auth_cookie
 Log debug-notice file /dev/null
+# UseBridges 1
+# ClientTransportPlugin obfs4 exec /usr/bin/obfs4proxy
+# Bridge obfs4 ip and so on

requirements.txt

@@ -2,12 +2,12 @@ attrs==22.2.0
 beautifulsoup4==4.11.2
 brotli==1.0.9
 cachelib==0.10.2
-certifi==2022.12.7
+certifi==2023.7.22
 cffi==1.15.1
 chardet==5.1.0
 click==8.1.3
 cryptography==3.3.2; platform_machine == 'armv7l'
-cryptography==41.0.0; platform_machine != 'armv7l'
+cryptography==41.0.4; platform_machine != 'armv7l'
 cssutils==2.6.0
 defusedxml==0.7.1
 Flask==2.3.2
@@ -29,7 +29,8 @@ python-dateutil==2.8.2
 requests==2.31.0
 soupsieve==2.4
 stem==1.8.1
-urllib3==1.26.14
+urllib3==1.26.17
+validators==0.22.0
 waitress==2.1.2
 wcwidth==0.2.6
 Werkzeug==2.3.3

run

@@ -29,6 +29,7 @@ else
         python3 -um app \
           --unix-socket "$UNIX_SOCKET"
     else
+        echo "Running on http://${ADDRESS:-0.0.0.0}:${PORT:-"${EXPOSE_PORT:-5000}"}"
         python3 -um app \
           --host "${ADDRESS:-0.0.0.0}" \
           --port "${PORT:-"${EXPOSE_PORT:-5000}"}"

test/test_results.py

@@ -44,17 +44,11 @@ def test_get_results(client):
 
 def test_post_results(client):
     rv = client.post(f'/{Endpoint.search}', data=dict(q='test'))
-    assert rv._status_code == 200
+    assert rv._status_code == 302
-
-    # Depending on the search, there can be more
-    # than 10 result divs
-    results = get_search_results(rv.data)
-    assert len(results) >= 10
-    assert len(results) <= 15
 
 
 def test_translate_search(client):
-    rv = client.post(f'/{Endpoint.search}', data=dict(q='translate hola'))
+    rv = client.get(f'/{Endpoint.search}?q=translate hola')
     assert rv._status_code == 200
 
     # Pretty weak test, but better than nothing
@@ -64,7 +58,7 @@ def test_translate_search(client):
 
 
 def test_block_results(client):
-    rv = client.post(f'/{Endpoint.search}', data=dict(q='pinterest'))
+    rv = client.get(f'/{Endpoint.search}?q=pinterest')
     assert rv._status_code == 200
 
     has_pinterest = False
@@ -79,7 +73,7 @@ def test_block_results(client):
     rv = client.post(f'/{Endpoint.config}', data=demo_config)
     assert rv._status_code == 302
 
-    rv = client.post(f'/{Endpoint.search}', data=dict(q='pinterest'))
+    rv = client.get(f'/{Endpoint.search}?q=pinterest')
     assert rv._status_code == 200
 
     for link in BeautifulSoup(rv.data, 'html.parser').find_all('a', href=True):
@@ -90,7 +84,7 @@ def test_block_results(client):
 
 
 def test_view_my_ip(client):
-    rv = client.post(f'/{Endpoint.search}', data=dict(q='my ip address'))
+    rv = client.get(f'/{Endpoint.search}?q=my ip address')
     assert rv._status_code == 200
 
     # Pretty weak test, but better than nothing
@@ -107,7 +101,7 @@ def test_recent_results(client):
     }
 
     for time, num_days in times.items():
-        rv = client.post(f'/{Endpoint.search}', data=dict(q='test :' + time))
+        rv = client.get(f'/{Endpoint.search}?q=test :' + time)
         result_divs = get_search_results(rv.data)
 
         current_date = datetime.now()