Fetching - Clarifying how fetchers work with SOCKS5 proxies

.github/workflows/test-only.yml

@@ -83,6 +83,7 @@ jobs:
         run: |
           cd changedetectionio
           ./run_proxy_tests.sh
+          # And again with PLAYWRIGHT_DRIVER_URL=..
           cd ..
 
       - name: Test changedetection.io container starts+runs basically without error

changedetectionio/content_fetcher.py

@@ -1,12 +1,15 @@
-import hashlib
 from abc import abstractmethod
+from distutils.util import strtobool
+from urllib.parse import urlparse
 import chardet
+import hashlib
 import json
 import logging
 import os
 import requests
 import sys
 import time
+import urllib.parse
 
 visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
 
@@ -266,7 +269,6 @@ class base_html_playwright(Fetcher):
 
         if self.proxy:
             # Playwright needs separate username and password values
-            from urllib.parse import urlparse
             parsed = urlparse(self.proxy.get('server'))
             if parsed.username:
                 self.proxy['username'] = parsed.username
@@ -321,14 +323,13 @@ class base_html_playwright(Fetcher):
 
         # Append proxy connect string
         if self.proxy:
-            import urllib.parse
             # Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
             # Actual authentication handled by Puppeteer/node
             o = urlparse(self.proxy.get('server'))
-            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
+            # Remove scheme, socks5:// doesnt always work and it will autodetect anyway
+            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl().replace(f"{o.scheme}://", '', 1))
             browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}&dumpio=true"
 
-
         try:
             amp = '&' if '?' in browserless_function_url else '?'
             response = requests.request(
@@ -347,7 +348,7 @@ class base_html_playwright(Fetcher):
                         'url': url,
                         'user_agent': {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
                         'proxy_username': self.proxy.get('username', '') if self.proxy else False,
-                        'proxy_password': self.proxy.get('password', '') if self.proxy else False,
+                        'proxy_password': self.proxy.get('password', '') if self.proxy and self.proxy.get('username') else False,
                         'no_cache_list': [
                             'twitter',
                             '.pdf'
@@ -416,8 +417,8 @@ class base_html_playwright(Fetcher):
                 lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
                 self.browser_steps))
 
-        if not has_browser_steps:
+        if not has_browser_steps and os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
-            if os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
+            if strtobool(os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH')):
                 # Temporary backup solution until we rewrite the playwright code
                 return self.run_fetch_browserless_puppeteer(
                     url,
@@ -434,6 +435,7 @@ class base_html_playwright(Fetcher):
 
         self.delete_browser_steps_screenshots()
         response = None
+
         with sync_playwright() as p:
             browser_type = getattr(p, self.browser_type)
 
@@ -442,6 +444,9 @@ class base_html_playwright(Fetcher):
             # 60,000 connection timeout only
             browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
 
+            # SOCKS5 with authentication is not supported (yet)
+            # https://github.com/microsoft/playwright/issues/10567
+
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
             context = browser.new_context(
@@ -478,7 +483,6 @@ class base_html_playwright(Fetcher):
                 print("Content Fetcher > retrying request got error - ", str(e))
                 time.sleep(1)
                 response = self.page.goto(url, wait_until='commit')
-
             except Exception as e:
                 print("Content Fetcher > Other exception when page.goto", str(e))
                 context.close()
@@ -614,7 +618,6 @@ class base_html_webdriver(Fetcher):
         from selenium.common.exceptions import WebDriverException
         # request_body, request_method unused for now, until some magic in the future happens.
 
-        # check env for WEBDRIVER_URL
         self.driver = webdriver.Remote(
             command_executor=self.command_executor,
             desired_capabilities=DesiredCapabilities.CHROME,
@@ -693,6 +696,10 @@ class html_requests(Fetcher):
         proxies = {}
 
         # Allows override the proxy on a per-request basis
+
+        # https://requests.readthedocs.io/en/latest/user/advanced/#socks
+        # Should also work with `socks5://user:pass@host:port` type syntax.
+
         if self.proxy_override:
             proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
         else:

changedetectionio/forms.py

@@ -481,7 +481,7 @@ class SingleExtraProxy(Form):
 
     # maybe better to set some <script>var..
     proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128", "size":50})
+    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
     # @todo do the validation here instead
 
 # datastore.data['settings']['requests']..

changedetectionio/res/puppeteer_fetch.js

@@ -18,6 +18,7 @@ module.exports = async ({page, context}) => {
 
     await page.setBypassCSP(true)
     await page.setExtraHTTPHeaders(req_headers);
+
     if (user_agent) {
         await page.setUserAgent(user_agent);
     }
@@ -26,6 +27,10 @@ module.exports = async ({page, context}) => {
     await page.setDefaultNavigationTimeout(0);
 
     if (proxy_username) {
+        // Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
+        // https://github.com/puppeteer/puppeteer/issues/676 ?
+        // https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
+        // https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
         await page.authenticate({
             username: proxy_username,
             password: proxy_password

changedetectionio/run_proxy_tests.sh

@@ -10,6 +10,40 @@ set -x
 docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 
+# SOCKS5 related - start simple Socks5 proxy server
+# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
+docker run --network changedet-network -d --hostname socks5proxy --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
+docker run --network changedet-network -d --hostname socks5proxy-noauth -p 1081:1080 --name socks5proxy-noauth  serjs/go-socks5-proxy
+
+echo "---------------------------------- SOCKS5 -------------------"
+# SOCKS5 related - test from proxies.json
+docker run --network changedet-network \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
+  --rm \
+  -e "SOCKSTEST=proxiesjson" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+# SOCKS5 related - by manually entering in UI
+docker run --network changedet-network \
+  --rm \
+  -e "SOCKSTEST=manual" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
+
+# SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
+docker run --network changedet-network \
+  -e "SOCKSTEST=manual-playwright" \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
+  -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" \
+  --rm \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+echo "socks5 server logs"
+docker logs socks5proxy
+echo "----------------------------------"
+
 # Used for configuring a custom proxy URL via the UI
 docker run --network changedet-network -d \
   --name squid-custom \

changedetectionio/store.py

@@ -42,6 +42,7 @@ class ChangeDetectionStore:
         self.__data = App.model()
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        print(">>> Datastore path is ", self.json_store_path)
         self.needs_write = False
         self.start_time = time.time()
         self.stop_thread = False

changedetectionio/templates/settings.html

@@ -230,6 +230,7 @@ nav
                 <div class="pure-control-group">
                 {{ render_field(form.requests.form.extra_proxies) }}
                 <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span>
+                <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
                 </div>
             </div>
             <div id="actions">

changedetectionio/tests/fetchers/test_content.py

@@ -28,8 +28,6 @@ def test_fetch_webdriver_content(client, live_server):
     )
 
     assert b"1 Imported" in res.data
-    time.sleep(3)
-
     wait_for_all_checks(client)
 
 

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -2,12 +2,11 @@
 
 import time
 from flask import url_for
-from ..util import live_server_setup
+from ..util import live_server_setup, wait_for_all_checks
+
 
 def test_preferred_proxy(client, live_server):
-    time.sleep(1)
     live_server_setup(live_server)
-    time.sleep(1)
     url = "http://chosen.changedetection.io"
 
     res = client.post(
@@ -20,7 +19,7 @@ def test_preferred_proxy(client, live_server):
 
     assert b"1 Imported" in res.data
 
-    time.sleep(2)
+    wait_for_all_checks(client)
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
@@ -34,5 +33,5 @@ def test_preferred_proxy(client, live_server):
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-    time.sleep(2)
+    wait_for_all_checks(client)
     # Now the request should appear in the second-squid logs

changedetectionio/tests/proxy_socks5/proxies.json-example

@@ -0,0 +1,6 @@
+{
+  "socks5proxy": {
+    "label": "socks5proxy",
+    "url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080"
+  }
+}

changedetectionio/tests/proxy_socks5/proxies.json-example-noauth

@@ -0,0 +1,6 @@
+{
+  "socks5proxy": {
+    "label": "socks5proxy",
+    "url": "socks5://socks5proxy-noauth:1080"
+  }
+}

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -0,0 +1,63 @@
+#!/usr/bin/python3
+import os
+import time
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+
+
+def test_socks5(client, live_server):
+    live_server_setup(live_server)
+
+    # Setup a proxy
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": "html_requests",
+            # set in .github/workflows/test-only.yml
+            "requests-extra_proxies-0-proxy_url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080",
+            "requests-extra_proxies-0-proxy_name": "socks5proxy",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.get(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+    )
+    # check the proxy is offered as expected
+    assert b'ui-0socks5proxy' in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+            "headers": "",
+            "proxy": "ui-0socks5proxy",
+            "tags": "",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Should see the proper string
+    assert "+0200:".encode('utf-8') in res.data

changedetectionio/tests/proxy_socks5/test_socks5_proxy_sources.py

@@ -0,0 +1,52 @@
+#!/usr/bin/python3
+import os
+import time
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+
+
+# should be proxies.json mounted from run_proxy_tests.sh already
+# -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json
+def test_socks5_from_proxiesjson_file(client, live_server):
+    live_server_setup(live_server)
+
+    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+
+    res = client.get(url_for("settings_page"))
+    assert b'name="requests-proxy" type="radio" value="socks5proxy"' in res.data
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.get(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+    )
+    # check the proxy is offered as expected
+    assert b'name="proxy" type="radio" value="socks5proxy"' in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+            "headers": "",
+            "proxy": "socks5proxy",
+            "tags": "",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Should see the proper string
+    assert "+0200:".encode('utf-8') in res.data

requirements.txt

@@ -16,7 +16,7 @@ validators~=0.21
 # Set these versions together to avoid a RequestsDependencyWarning
 # >= 2.26 also adds Brotli support if brotli is installed
 brotli~=1.0
-requests[socks] ~=2.28
+requests[socks]
 
 urllib3>1.26
 chardet>2.3.0