WIP

2025-10-31 22:57:18 +00:00 · 2023-06-23 15:22:13 +02:00
4 changed files with 11 additions and 6 deletions
--- a/changedetectionio/forms.py
+++ b/changedetectionio/forms.py
@@ -316,10 +316,11 @@ class ValidateCSSJSONXPATHInput(object):
                if not self.allow_xpath:
                    raise ValidationError("XPath not permitted in this field!")
                from lxml import etree, html
+                import elementpath
                tree = html.fromstring("<html></html>")

                try:
-                    tree.xpath(line.strip())
+                    elementpath.select(tree, line)
                except etree.XPathEvalError as e:
                    message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
                    raise ValidationError(message % (line, str(e)))
--- a/changedetectionio/html_tools.py
+++ b/changedetectionio/html_tools.py
@@ -51,12 +51,13 @@ def element_removal(selectors: List[str], html_content):

 # Return str Utf-8 of matched rules
 def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
+    import elementpath
    from lxml import etree, html

    tree = html.fromstring(bytes(html_content, encoding='utf-8'))
    html_block = ""

-    r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
+    r = elementpath.select(tree, xpath_filter.strip())
    #@note: //title/text() wont work where <title>CDATA..

    for element in r:
--- a/changedetectionio/tests/test_xpath_selector.py
+++ b/changedetectionio/tests/test_xpath_selector.py
@@ -2,7 +2,7 @@

 import time
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks

 from ..html_tools import *

@@ -164,6 +164,7 @@ def test_check_xpath_text_function_utf8(client, live_server):
    assert b'Deleted' in res.data

 def test_check_markup_xpath_filter_restriction(client, live_server):
+    live_server_setup(live_server)
    sleep_time_for_fetch_thread = 3

    xpath_filter = "//*[contains(@class, 'sametext')]"
@@ -183,7 +184,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
    assert b"1 Imported" in res.data

    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)

    # Goto the edit page, add our ignore text
    # Add our URL to the import page
@@ -195,7 +196,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
    assert b"Updated watch." in res.data

    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)

    # view it/reset state back to viewed
    client.get(url_for("diff_history_page", uuid="first"), follow_redirects=True)
@@ -206,7 +207,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
    # Trigger a check
    client.get(url_for("form_watch_checknow"), follow_redirects=True)
    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)

    res = client.get(url_for("index"))
    assert b'unviewed' not in res.data
--- a/requirements.txt
+++ b/requirements.txt
@@ -42,6 +42,8 @@ paho-mqtt
 # (introduced once apprise became a dep)
 cryptography~=3.4

+elementpath
+
 # Used for CSS filtering
 beautifulsoup4