Merge branch 'master' into optional-proxy-via-ui

changedetectionio/content_fetcher.py

@@ -243,6 +243,14 @@ class base_html_playwright(Fetcher):
         if proxy_override:
             self.proxy = {'server': proxy_override}
 
+        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
+                self.proxy['password'] = parsed.password
+
     def screenshot_step(self, step_n=''):
 
         # There's a bug where we need to do it twice or it doesnt take the whole page, dont know why.
@@ -370,7 +378,7 @@ class base_html_playwright(Fetcher):
                 context.close()
                 browser.close()
                 print ("Content Fetcher > Content was empty")
-                raise EmptyReply(url=url, status_code=None)
+                raise EmptyReply(url=url, status_code=response.status)
 
             # Bug 2(?) Set the viewport size AFTER loading the page
             self.page.set_viewport_size({"width": 1280, "height": 1024})

changedetectionio/forms.py

@@ -426,6 +426,13 @@ class watchForm(commonSettingsForm):
         return result
 
 
+class SingleExtraProxy(Form):
+
+    # maybe better to set some <script>var..
+    proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
+    proxy_url = StringField('URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128"})
+    # @todo do the validation here instead
+
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
@@ -433,6 +440,15 @@ class globalSettingsRequestForm(Form):
     jitter_seconds = IntegerField('Random jitter seconds ± check',
                                   render_kw={"style": "width: 5em;"},
                                   validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
+    extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
+
+    def validate_extra_proxies(self, extra_validators=None):
+        for e in self.data['extra_proxies']:
+            if e.get('proxy_name') or e.get('proxy_url'):
+                if not e.get('proxy_name','').strip() or not e.get('proxy_url','').strip():
+                    self.extra_proxies.errors.append('Both a name, and a Proxy URL is required.')
+                    return False
+
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):

changedetectionio/model/App.py

@@ -15,11 +15,12 @@ class model(dict):
                 'headers': {
                 },
                 'requests': {
-                    'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
-                    'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
+                    'extra_proxies': [], # Configurable extra proxies via the UI
                     'jitter_seconds': 0,
+                    'proxy': None, # Preferred proxy connection
+                    'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
+                    'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
                     'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
-                    'proxy': None # Preferred proxy connection
                 },
                 'application': {
                     'api_access_token_enabled': True,

changedetectionio/run_proxy_tests.sh

@@ -8,6 +8,15 @@ set -e
 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
 
+# Used for configuring a custom proxy URL via the UI
+docker run --network changedet-network -d \
+  --name squid-custom \
+  --hostname squid-squid-custom \
+  --rm \
+  -v `pwd`/tests/proxy_list/squid-auth.conf:/etc/squid/conf.d/debian.conf \
+  -v `pwd`/tests/proxy_list/squid-passwords.txt:/etc/squid3/passwords \
+  ubuntu/squid:4.13-21.10_edge
+
 
 ## 2nd test actually choose the preferred proxy from proxies.json
 
@@ -32,3 +41,19 @@ then
   echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid two)"
   exit 1
 fi
+
+
+# Test the UI configurable proxies
+
+docker run --network changedet-network \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_select_custom_proxy.py'
+
+
+# Should see a request for one.changedetection.io in there
+docker logs squid-custom 2>/dev/null|grep "TCP_TUNNEL.200.*changedetection.io"
+if [ $? -ne 0 ]
+then
+  echo "Did not see a valid request to changedetection.io in the squid logs (while checking preferred proxy - squid two)"
+  exit 1
+fi

changedetectionio/static/styles/scss/parts/_extra_proxies.scss

@@ -0,0 +1,17 @@
+ul#requests-extra_proxies {
+  list-style: none;
+  /* tidy up the table to look more "inline" */
+  li {
+    > label {
+      display: none;
+    }
+
+  }
+  /* each proxy entry is a `table` */
+  table {
+    tr {
+      display: inline;
+    }
+  }
+}
+

changedetectionio/static/styles/scss/styles.scss

@@ -2,10 +2,11 @@
  * -- BASE STYLES --
  */
 
-@import "parts/_variables";
-@import "parts/_spinners";
-@import "parts/_browser-steps";
 @import "parts/_arrows";
+@import "parts/_browser-steps";
+@import "parts/_extra_proxies";
+@import "parts/_spinners";
+@import "parts/_variables";
 
 body {
   color: var(--color-text);

changedetectionio/static/styles/styles.css

@@ -1,6 +1,139 @@
 /*
  * -- BASE STYLES --
  */
+.arrow {
+  border: solid #1b98f8;
+  border-width: 0 2px 2px 0;
+  display: inline-block;
+  padding: 3px; }
+  .arrow.right {
+    transform: rotate(-45deg);
+    -webkit-transform: rotate(-45deg); }
+  .arrow.left {
+    transform: rotate(135deg);
+    -webkit-transform: rotate(135deg); }
+  .arrow.up, .arrow.asc {
+    transform: rotate(-135deg);
+    -webkit-transform: rotate(-135deg); }
+  .arrow.down, .arrow.desc {
+    transform: rotate(45deg);
+    -webkit-transform: rotate(45deg); }
+
+#browser_steps {
+  /* convert rows to horizontal cells */ }
+  #browser_steps th {
+    display: none; }
+  #browser_steps li {
+    list-style: decimal;
+    padding: 5px; }
+    #browser_steps li:not(:first-child):hover {
+      opacity: 1.0; }
+    #browser_steps li .control {
+      padding-left: 5px;
+      padding-right: 5px; }
+      #browser_steps li .control a {
+        font-size: 70%; }
+    #browser_steps li.empty {
+      padding: 0px;
+      opacity: 0.35; }
+      #browser_steps li.empty .control {
+        display: none; }
+    #browser_steps li:hover {
+      background: #eee; }
+    #browser_steps li > label {
+      display: none; }
+
+#browser-steps-fieldlist {
+  height: 100%;
+  overflow-y: scroll; }
+
+#browser-steps .flex-wrapper {
+  display: flex;
+  flex-flow: row;
+  height: 600px;
+  /*@todo make this dynamic */ }
+
+/*  this is duplicate :( */
+#browsersteps-selector-wrapper {
+  height: 100%;
+  width: 100%;
+  overflow-y: scroll;
+  position: relative;
+  /* nice tall skinny one */ }
+  #browsersteps-selector-wrapper > img {
+    position: absolute;
+    max-width: 100%; }
+  #browsersteps-selector-wrapper > canvas {
+    position: relative;
+    max-width: 100%; }
+    #browsersteps-selector-wrapper > canvas:hover {
+      cursor: pointer; }
+  #browsersteps-selector-wrapper .loader {
+    position: absolute;
+    left: 50%;
+    top: 50%;
+    transform: translate(-50%, -50%);
+    margin-left: -40px;
+    z-index: 100;
+    max-width: 350px;
+    text-align: center; }
+  #browsersteps-selector-wrapper .spinner, #browsersteps-selector-wrapper .spinner:after {
+    width: 80px;
+    height: 80px;
+    font-size: 3px; }
+  #browsersteps-selector-wrapper #browsersteps-click-start {
+    color: var(--color-grey-400); }
+    #browsersteps-selector-wrapper #browsersteps-click-start:hover {
+      cursor: pointer; }
+
+ul#requests-extra_proxies {
+  list-style: none;
+  /* tidy up the table to look more "inline" */
+  /* each proxy entry is a `table` */ }
+  ul#requests-extra_proxies li > label {
+    display: none; }
+  ul#requests-extra_proxies table tr {
+    display: inline; }
+
+/* spinner */
+.spinner,
+.spinner:after {
+  border-radius: 50%;
+  width: 10px;
+  height: 10px; }
+
+.spinner {
+  margin: 0px auto;
+  font-size: 3px;
+  vertical-align: middle;
+  display: inline-block;
+  text-indent: -9999em;
+  border-top: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-right: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-bottom: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-left: 1.1em solid #2668ed;
+  -webkit-transform: translateZ(0);
+  -ms-transform: translateZ(0);
+  transform: translateZ(0);
+  -webkit-animation: load8 1.1s infinite linear;
+  animation: load8 1.1s infinite linear; }
+
+@-webkit-keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }
+
+@keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }
+
 /**
  * CSS custom properties (aka variables).
  */
@@ -138,130 +271,6 @@ html[data-darkmode="true"] {
     html[data-darkmode="true"] .watch-table .unviewed.error {
       color: var(--color-watch-table-error); }
 
-/* spinner */
-.spinner,
-.spinner:after {
-  border-radius: 50%;
-  width: 10px;
-  height: 10px; }
-
-.spinner {
-  margin: 0px auto;
-  font-size: 3px;
-  vertical-align: middle;
-  display: inline-block;
-  text-indent: -9999em;
-  border-top: 1.1em solid rgba(38, 104, 237, 0.2);
-  border-right: 1.1em solid rgba(38, 104, 237, 0.2);
-  border-bottom: 1.1em solid rgba(38, 104, 237, 0.2);
-  border-left: 1.1em solid #2668ed;
-  -webkit-transform: translateZ(0);
-  -ms-transform: translateZ(0);
-  transform: translateZ(0);
-  -webkit-animation: load8 1.1s infinite linear;
-  animation: load8 1.1s infinite linear; }
-
-@-webkit-keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg); }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg); } }
-
-@keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg); }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg); } }
-
-#browser_steps {
-  /* convert rows to horizontal cells */ }
-  #browser_steps th {
-    display: none; }
-  #browser_steps li {
-    list-style: decimal;
-    padding: 5px; }
-    #browser_steps li:not(:first-child):hover {
-      opacity: 1.0; }
-    #browser_steps li .control {
-      padding-left: 5px;
-      padding-right: 5px; }
-      #browser_steps li .control a {
-        font-size: 70%; }
-    #browser_steps li.empty {
-      padding: 0px;
-      opacity: 0.35; }
-      #browser_steps li.empty .control {
-        display: none; }
-    #browser_steps li:hover {
-      background: #eee; }
-    #browser_steps li > label {
-      display: none; }
-
-#browser-steps-fieldlist {
-  height: 100%;
-  overflow-y: scroll; }
-
-#browser-steps .flex-wrapper {
-  display: flex;
-  flex-flow: row;
-  height: 600px;
-  /*@todo make this dynamic */ }
-
-/*  this is duplicate :( */
-#browsersteps-selector-wrapper {
-  height: 100%;
-  width: 100%;
-  overflow-y: scroll;
-  position: relative;
-  /* nice tall skinny one */ }
-  #browsersteps-selector-wrapper > img {
-    position: absolute;
-    max-width: 100%; }
-  #browsersteps-selector-wrapper > canvas {
-    position: relative;
-    max-width: 100%; }
-    #browsersteps-selector-wrapper > canvas:hover {
-      cursor: pointer; }
-  #browsersteps-selector-wrapper .loader {
-    position: absolute;
-    left: 50%;
-    top: 50%;
-    transform: translate(-50%, -50%);
-    margin-left: -40px;
-    z-index: 100;
-    max-width: 350px;
-    text-align: center; }
-  #browsersteps-selector-wrapper .spinner, #browsersteps-selector-wrapper .spinner:after {
-    width: 80px;
-    height: 80px;
-    font-size: 3px; }
-  #browsersteps-selector-wrapper #browsersteps-click-start {
-    color: var(--color-grey-400); }
-    #browsersteps-selector-wrapper #browsersteps-click-start:hover {
-      cursor: pointer; }
-
-.arrow {
-  border: solid #1b98f8;
-  border-width: 0 2px 2px 0;
-  display: inline-block;
-  padding: 3px; }
-  .arrow.right {
-    transform: rotate(-45deg);
-    -webkit-transform: rotate(-45deg); }
-  .arrow.left {
-    transform: rotate(135deg);
-    -webkit-transform: rotate(135deg); }
-  .arrow.up, .arrow.asc {
-    transform: rotate(-135deg);
-    -webkit-transform: rotate(-135deg); }
-  .arrow.down, .arrow.desc {
-    transform: rotate(45deg);
-    -webkit-transform: rotate(45deg); }
-
 body {
   color: var(--color-text);
   background: var(--color-background-page); }

changedetectionio/store.py

@@ -36,7 +36,6 @@ class ChangeDetectionStore:
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
         self.needs_write = False
-        self.proxy_list = None
         self.start_time = time.time()
         self.stop_thread = False
         # Base definition for all watchers
@@ -116,11 +115,6 @@ class ChangeDetectionStore:
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['api_access_token'] = secret
 
-        # Proxy list support - available as a selection in settings when text file is imported
-        proxy_list_file = "{}/proxies.json".format(self.datastore_path)
-        if path.isfile(proxy_list_file):
-            self.import_proxy_list(proxy_list_file)
-
         # Bump the update version by running updates
         self.run_updates()
 
@@ -463,10 +457,30 @@ class ChangeDetectionStore:
                     print ("Removing",item)
                     unlink(item)
 
-    def import_proxy_list(self, filename):
-        with open(filename) as f:
-            self.proxy_list = json.load(f)
-            print ("Registered proxy list", list(self.proxy_list.keys()))
+    @property
+    def proxy_list(self):
+        proxy_list = {}
+        proxy_list_file = os.path.join(self.datastore_path, 'proxies.json')
+
+        # Load from external config file
+        if path.isfile(proxy_list_file):
+            with open("{}/proxies.json".format(self.datastore_path)) as f:
+                proxy_list = json.load(f)
+
+        # Mapping from UI config if available
+        extras = self.data['settings']['requests'].get('extra_proxies')
+        if extras:
+            i=0
+            for proxy in extras:
+                i += 0
+                if proxy.get('proxy_name') and proxy.get('proxy_url'):
+                    k = "ui-" + str(i) + proxy.get('proxy_name')
+                    proxy_list[k] = {'label': proxy.get('proxy_name'), 'url': proxy.get('proxy_url')}
+
+
+        return proxy_list if len(proxy_list) else None
+
+
 
 
     def get_preferred_proxy_for_watch(self, uuid):
@@ -476,11 +490,10 @@ class ChangeDetectionStore:
         :return: proxy "key" id
         """
 
-        proxy_id = None
         if self.proxy_list is None:
             return None
 
-        # If its a valid one
+        # If it's a valid one
         watch = self.data['watching'].get(uuid)
 
         if watch.get('proxy') and watch.get('proxy') in list(self.proxy_list.keys()):
@@ -493,8 +506,9 @@ class ChangeDetectionStore:
             if self.proxy_list.get(system_proxy_id):
                 return system_proxy_id
 
-        # Fallback - Did not resolve anything, use the first available
-        if system_proxy_id is None:
+
+        # Fallback - Did not resolve anything, or doesnt exist, use the first available
+        if system_proxy_id is None or not self.proxy_list.get(system_proxy_id):
             first_default = list(self.proxy_list)[0]
             return first_default
 

changedetectionio/templates/settings.html

@@ -21,6 +21,7 @@
             <li class="tab"><a href="#fetching">Fetching</a></li>
             <li class="tab"><a href="#filters">Global Filters</a></li>
             <li class="tab"><a href="#api">API</a></li>
+            <li class="tab"><a href="#proxies">CAPTCHA &amp; Proxies</a></li>
         </ul>
     </div>
     <div class="box-wrap inner">
@@ -170,7 +171,21 @@ nav
                     </div>
                 </div>
             </div>
+            <div class="tab-pane-inner" id="proxies">
 
+                <p><strong>Tip</strong>: You can connect <a href="https://brightdata.grsm.io/n0r16zf7eivq">BrightData <strong>WebUnlocker</strong></a> proxies to work around CAPTCHA.<br/>
+                    Simply <a href="https://brightdata.grsm.io/n0r16zf7eivq">register</a> and paste in the Proxy URL below.<br/>
+                    You can also add extra location/country proxies.</br>
+                </p>
+
+                <p>Please use our referrer link for BrightData <a href="https://brightdata.grsm.io/n0r16zf7eivq">https://brightdata.grsm.io/n0r16zf7eivq</a></p>
+
+
+                <div class="pure-control-group">
+                    {{ render_field(form.requests.form.extra_proxies) }}
+
+                </div>
+            </div>
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}

changedetectionio/tests/proxy_list/squid-auth.conf

@@ -0,0 +1,48 @@
+acl localnet src 0.0.0.1-0.255.255.255  # RFC 1122 "this" network (LAN)
+acl localnet src 10.0.0.0/8             # RFC 1918 local private network (LAN)
+acl localnet src 100.64.0.0/10          # RFC 6598 shared address space (CGN)
+acl localnet src 169.254.0.0/16         # RFC 3927 link-local (directly plugged) machines
+acl localnet src 172.16.0.0/12          # RFC 1918 local private network (LAN)
+acl localnet src 192.168.0.0/16         # RFC 1918 local private network (LAN)
+acl localnet src fc00::/7               # RFC 4193 local private network range
+acl localnet src fe80::/10              # RFC 4291 link-local (directly plugged) machines
+acl localnet src 159.65.224.174
+acl SSL_ports port 443
+acl Safe_ports port 80          # http
+acl Safe_ports port 21          # ftp
+acl Safe_ports port 443         # https
+acl Safe_ports port 70          # gopher
+acl Safe_ports port 210         # wais
+acl Safe_ports port 1025-65535  # unregistered ports
+acl Safe_ports port 280         # http-mgmt
+acl Safe_ports port 488         # gss-http
+acl Safe_ports port 591         # filemaker
+acl Safe_ports port 777         # multiling http
+acl CONNECT method CONNECT
+
+http_access deny !Safe_ports
+http_access deny CONNECT !SSL_ports
+#http_access allow localhost manager
+http_access deny manager
+#http_access allow localhost
+#http_access allow localnet
+
+auth_param basic program /usr/lib/squid3/basic_ncsa_auth /etc/squid3/passwords
+auth_param basic realm proxy
+acl authenticated proxy_auth REQUIRED
+http_access allow authenticated
+http_access deny all
+
+
+http_port 3128
+coredump_dir /var/spool/squid
+refresh_pattern ^ftp:           1440    20%     10080
+refresh_pattern ^gopher:        1440    0%      1440
+refresh_pattern -i (/cgi-bin/|\?) 0     0%      0
+refresh_pattern \/(Packages|Sources)(|\.bz2|\.gz|\.xz)$ 0 0% 0 refresh-ims
+refresh_pattern \/Release(|\.gpg)$ 0 0% 0 refresh-ims
+refresh_pattern \/InRelease$ 0 0% 0 refresh-ims
+refresh_pattern \/(Translation-.*)(|\.bz2|\.gz|\.xz)$ 0 0% 0 refresh-ims
+refresh_pattern .               0       20%     4320
+logfile_rotate 0
+

changedetectionio/tests/proxy_list/squid-passwords.txt

@@ -0,0 +1 @@
+test:$apr1$xvhFolTA$E/kz5/Rw1ewcyaSUdwqZs.

changedetectionio/tests/proxy_list/test_select_custom_proxy.py

@@ -0,0 +1,51 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks
+
+# just make a request, we will grep in the docker logs to see it actually got called
+def test_select_custom(client, live_server):
+    live_server_setup(live_server)
+
+    # Goto settings, add our custom one
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": "html_requests",
+            "requests-extra_proxies-0-proxy_name": "custom-test-proxy",
+            # test:awesome is set in tests/proxy_list/squid-passwords.txt
+            "requests-extra_proxies-0-proxy_url": "http://test:awesome@squid-custom:3128",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    res = client.post(
+        url_for("import_page"),
+        # Because a URL wont show in squid/proxy logs due it being SSLed
+        # Use plain HTTP or a specific domain-name here
+        data={"urls": "https://changedetection.io/CHANGELOG.txt"},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(url_for("index"))
+    assert b'Proxy Authentication Required' not in res.data
+
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    # We should see something via proxy
+    assert b'HEAD' in res.data
+
+    #
+    # Now we should see the request in the container logs for "squid-squid-custom" because it will be the only default
+