Try to get browsersteps working on mobile better

changedetectionio/flask_app.py

@@ -1432,6 +1432,7 @@ def changedetection_app(config=None, datastore_o=None):
                                                                      )
                 # Use the last loaded HTML as the input
                 update_handler.fetcher.content = decompressed_data
+                update_handler.fetcher.headers['content-type'] = tmp_watch.get('content-type')
                 try:
                     changed_detected, update_obj, contents, text_after_filter = update_handler.run_changedetection(
                         watch=tmp_watch,

changedetectionio/model/__init__.py

@@ -18,6 +18,7 @@ class watch_base(dict):
             'check_count': 0,
             'check_unique_lines': False,  # On change-detected, compare against all history if its something new
             'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'content-type': None,
             'date_created': None,
             'extract_text': [],  # Extract text by regex after filters
             'extract_title_as_title': False,

changedetectionio/processors/restock_diff/processor.py

@@ -143,8 +143,6 @@ class perform_site_check(difference_detection_processor):
     def run_changedetection(self, watch, skip_when_checksum_same=True):
         import hashlib
 
-        from concurrent.futures import ProcessPoolExecutor
-        from functools import partial
         if not watch:
             raise Exception("Watch no longer exists.")
 
@@ -186,11 +184,7 @@ class perform_site_check(difference_detection_processor):
 
         itemprop_availability = {}
         try:
-            with ProcessPoolExecutor() as executor:
-                # Use functools.partial to create a callable with arguments
-                # anything using bs4/lxml etc is quite "leaky"
-                future = executor.submit(partial(get_itemprop_availability, self.fetcher.content))
-                itemprop_availability = future.result()
+            itemprop_availability = get_itemprop_availability(self.fetcher.content)
         except MoreThanOnePriceFound as e:
             # Add the real data
             raise ProcessorException(message="Cannot run, more than one price detected, this plugin is only for product pages with ONE product, try the content-change detection mode.",

changedetectionio/processors/text_json_diff/processor.py

@@ -36,8 +36,6 @@ class PDFToHTMLToolNotFound(ValueError):
 class perform_site_check(difference_detection_processor):
 
     def run_changedetection(self, watch, skip_when_checksum_same=True):
-        from concurrent.futures import ProcessPoolExecutor
-        from functools import partial
 
         changed_detected = False
         html_content = ""
@@ -174,30 +172,20 @@ class perform_site_check(difference_detection_processor):
                     for filter_rule in include_filters_rule:
                         # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
                         if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
-                            with ProcessPoolExecutor() as executor:
-                                # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                                future = executor.submit(partial(html_tools.xpath_filter, xpath_filter=filter_rule.replace('xpath:', ''),
+                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
                                                                     html_content=self.fetcher.content,
                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                    is_rss=is_rss))
-                                html_content += future.result()
+                                                                    is_rss=is_rss)
 
                         elif filter_rule.startswith('xpath1:'):
-                            with ProcessPoolExecutor() as executor:
-                                # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                                future = executor.submit(partial(html_tools.xpath1_filter, xpath_filter=filter_rule.replace('xpath1:', ''),
-                                                                    html_content=self.fetcher.content,
-                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                    is_rss=is_rss))
-                                html_content += future.result()
+                            html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
+                                                                     html_content=self.fetcher.content,
+                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                     is_rss=is_rss)
                         else:
-                            with ProcessPoolExecutor() as executor:
-                                # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                                # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                                future = executor.submit(partial(html_tools.include_filters, include_filters=filter_rule,
+                            html_content += html_tools.include_filters(include_filters=filter_rule,
                                                                        html_content=self.fetcher.content,
-                                                                       append_pretty_line_formatting=not watch.is_source_type_url))
-                                html_content += future.result()
+                                                                       append_pretty_line_formatting=not watch.is_source_type_url)
 
                     if not html_content.strip():
                         raise FilterNotFoundInResponse(msg=include_filters_rule, screenshot=self.fetcher.screenshot, xpath_data=self.fetcher.xpath_data)
@@ -210,20 +198,16 @@ class perform_site_check(difference_detection_processor):
                 else:
                     # extract text
                     do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
-                    with ProcessPoolExecutor() as executor:
-                        # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                        # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                        future = executor.submit(partial(html_tools.html_to_text, html_content=html_content,
-                            render_anchor_tag_content=do_anchor,
-                            is_rss=is_rss)) #1874 activate the <title workaround hack
-                        stripped_text_from_html = future.result()
+                    stripped_text_from_html = html_tools.html_to_text(html_content=html_content,
+                                                                      render_anchor_tag_content=do_anchor,
+                                                                      is_rss=is_rss)  # 1874 activate the <title workaround hack
 
 
         if watch.get('trim_text_whitespace'):
             stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
 
         if watch.get('remove_duplicate_lines'):
-            stripped_text_from_html = '\n'.join(dict.fromkeys(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
+            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
 
         if watch.get('sort_text_alphabetically'):
             # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap

changedetectionio/static/js/watch-settings.js

@@ -34,6 +34,7 @@ function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
 
 function request_textpreview_update() {
     if (!$('body').hasClass('preview-text-enabled')) {
+        console.error("Preview text was requested but body tag was not setup")
         return
     }
 
@@ -77,20 +78,19 @@ $(document).ready(function () {
 
     const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
     $("#text-preview-inner").css('max-height', (vh-300)+"px");
+
+    // Realtime preview of 'Filters & Text' setup
     var debounced_request_textpreview_update = request_textpreview_update.debounce(100);
 
     $("#activate-text-preview").click(function (e) {
-        $(this).fadeOut();
         $('body').toggleClass('preview-text-enabled')
-
         request_textpreview_update();
 
-        $("#text-preview-refresh").click(function (e) {
-            request_textpreview_update();
-        });
-        $('textarea:visible').on('keyup blur', debounced_request_textpreview_update);
-        $('input:visible').on('keyup blur change', debounced_request_textpreview_update);
-        $("#filters-and-triggers-tab").on('click', debounced_request_textpreview_update);
+        const method = $('body').hasClass('preview-text-enabled') ? 'on' : 'off';
+        $("#text-preview-refresh")[method]('click', debounced_request_textpreview_update);
+        $('textarea:visible')[method]('keyup blur', debounced_request_textpreview_update);
+        $('input:visible')[method]('keyup blur change', debounced_request_textpreview_update);
+        $("#filters-and-triggers-tab")[method]('click', debounced_request_textpreview_update);
     });
 
 });

changedetectionio/static/styles/scss/parts/_browser-steps.scss

@@ -42,26 +42,36 @@
 
 
 #browser-steps .flex-wrapper {
-  display: flex;
-  flex-flow: row;
-  height: 70vh;
   font-size: 80%;
-  #browser-steps-ui {
-    flex-grow: 1;      /* Allow it to grow and fill the available space */
-    flex-shrink: 1;    /* Allow it to shrink if needed */
-    flex-basis: 0;     /* Start with 0 base width so it stretches as much as possible */
-    background-color: #eee;
-    border-radius: 5px;
 
+  @media screen and (min-width: 800px) {
+    display: flex;
+    flex-flow: row;
+    height: 70vh;
+    #browser-steps-fieldlist {
+      flex-grow: 0; /* Don't allow it to grow */
+      flex-shrink: 0; /* Don't allow it to shrink */
+      flex-basis: auto; /* Base width is determined by the content */
+      max-width: 400px; /* Set a max width to prevent overflow */
+      padding-left: 1rem;
+      overflow-y: scroll;
+    }
+
+
+    #browser-steps-ui {
+      flex-grow: 1; /* Allow it to grow and fill the available space */
+      flex-shrink: 1; /* Allow it to shrink if needed */
+      flex-basis: 0; /* Start with 0 base width so it stretches as much as possible */
+    }
   }
 
-  #browser-steps-fieldlist {
-    flex-grow: 0;      /* Don't allow it to grow */
-    flex-shrink: 0;    /* Don't allow it to shrink */
-    flex-basis: auto;  /* Base width is determined by the content */
-    max-width: 400px;  /* Set a max width to prevent overflow */
-    padding-left: 1rem;
-    overflow-y: scroll;
+  #browser-steps-ui {
+    background-color: #eee;
+    border-radius: 5px;
+  }
+
+  #browser-steps-field-list {
+    text-align: center;
   }
 }
 

changedetectionio/static/styles/styles.css

@@ -47,30 +47,35 @@
       display: none; }
 
 #browser-steps .flex-wrapper {
-  display: flex;
-  flex-flow: row;
-  height: 70vh;
   font-size: 80%; }
+  @media screen and (min-width: 800px) {
+    #browser-steps .flex-wrapper {
+      display: flex;
+      flex-flow: row;
+      height: 70vh; }
+      #browser-steps .flex-wrapper #browser-steps-fieldlist {
+        flex-grow: 0;
+        /* Don't allow it to grow */
+        flex-shrink: 0;
+        /* Don't allow it to shrink */
+        flex-basis: auto;
+        /* Base width is determined by the content */
+        max-width: 400px;
+        /* Set a max width to prevent overflow */
+        padding-left: 1rem;
+        overflow-y: scroll; }
+      #browser-steps .flex-wrapper #browser-steps-ui {
+        flex-grow: 1;
+        /* Allow it to grow and fill the available space */
+        flex-shrink: 1;
+        /* Allow it to shrink if needed */
+        flex-basis: 0;
+        /* Start with 0 base width so it stretches as much as possible */ } }
   #browser-steps .flex-wrapper #browser-steps-ui {
-    flex-grow: 1;
-    /* Allow it to grow and fill the available space */
-    flex-shrink: 1;
-    /* Allow it to shrink if needed */
-    flex-basis: 0;
-    /* Start with 0 base width so it stretches as much as possible */
     background-color: #eee;
     border-radius: 5px; }
-  #browser-steps .flex-wrapper #browser-steps-fieldlist {
-    flex-grow: 0;
-    /* Don't allow it to grow */
-    flex-shrink: 0;
-    /* Don't allow it to shrink */
-    flex-basis: auto;
-    /* Base width is determined by the content */
-    max-width: 400px;
-    /* Set a max width to prevent overflow */
-    padding-left: 1rem;
-    overflow-y: scroll; }
+  #browser-steps .flex-wrapper #browser-steps-field-list {
+    text-align: center; }
 
 /*  this is duplicate :( */
 #browsersteps-selector-wrapper {

changedetectionio/tests/test_encoding.py

@@ -3,7 +3,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks
+from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 import pytest
 
 
@@ -38,6 +38,11 @@ def test_check_encoding_detection(client, live_server, measure_memory_usage):
     # Give the thread time to pick it up
     wait_for_all_checks(client)
 
+
+    # Content type recording worked
+    uuid = extract_UUID_from_client(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['content-type'] == "text/html"
+
     res = client.get(
         url_for("preview_page", uuid="first"),
         follow_redirects=True

changedetectionio/update_worker.py

@@ -491,6 +491,8 @@ class update_worker(threading.Thread):
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
+                        update_obj['content-type'] = update_handler.fetcher.get_all_headers().get('content-type', '').lower()
+
                         # Mark that we never had any failures
                         if not watch.get('ignore_status_codes'):
                             update_obj['consecutive_filter_failures'] = 0