Re #2568 Add encoding for scraper script reader

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.01'
+__version__ = '0.46.02'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/content_fetchers/base.py

@@ -65,8 +65,8 @@ class Fetcher():
 
     def __init__(self):
         import importlib.resources
-        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
-        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text()
+        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
+        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
 
     @abstractmethod
     def get_error(self):
@@ -81,7 +81,8 @@ class Fetcher():
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
         # Should set self.error, self.status_code and self.content
         pass
 

changedetectionio/content_fetchers/playwright.py

@@ -83,7 +83,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._errors
@@ -130,7 +131,7 @@ class fetcher(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Response object was none")
+                logger.debug("Content Fetcher > Response object from the browser communication was none")
                 raise EmptyReply(url=url, status_code=None)
 
             try:
@@ -166,10 +167,10 @@ class fetcher(Fetcher):
 
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
-            if len(self.page.content().strip()) == 0:
+            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
+                logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
             # Run Browser Steps here

changedetectionio/content_fetchers/puppeteer.py

@@ -75,7 +75,8 @@ class fetcher(Fetcher):
                          request_method,
                          ignore_status_codes,
                          current_include_filters,
-                         is_binary
+                         is_binary,
+                         empty_pages_are_a_change
                          ):
 
         from changedetectionio.content_fetchers import visualselector_xpath_selectors
@@ -153,7 +154,7 @@ class fetcher(Fetcher):
         if response is None:
             await self.page.close()
             await browser.close()
-            logger.warning("Content Fetcher > Response object was none")
+            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
             raise EmptyReply(url=url, status_code=None)
 
         self.headers = response.headers
@@ -186,10 +187,11 @@ class fetcher(Fetcher):
 
             raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
         content = await self.page.content
-        if len(content.strip()) == 0:
+
+        if not empty_pages_are_a_change and len(content.strip()) == 0:
+            logger.error("Content Fetcher > Content was empty (empty_pages_are_a_change is False), closing browsers")
             await self.page.close()
             await browser.close()
-            logger.error("Content Fetcher > Content was empty")
             raise EmptyReply(url=url, status_code=response.status)
 
         # Run Browser Steps here
@@ -247,7 +249,7 @@ class fetcher(Fetcher):
         await self.fetch_page(**kwargs)
 
     def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False):
+            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
 
         #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
         max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
@@ -262,7 +264,8 @@ class fetcher(Fetcher):
                 request_method=request_method,
                 ignore_status_codes=ignore_status_codes,
                 current_include_filters=current_include_filters,
-                is_binary=is_binary
+                is_binary=is_binary,
+                empty_pages_are_a_change=empty_pages_are_a_change
             ), timeout=max_time))
         except asyncio.TimeoutError:
             raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))

changedetectionio/content_fetchers/requests.py

@@ -1,9 +1,8 @@
+from loguru import logger
+import chardet
 import hashlib
 import os
-
-import chardet
 import requests
-
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -26,7 +25,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
@@ -74,7 +74,10 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
+            if not empty_pages_are_a_change:
+                raise EmptyReply(url=url, status_code=r.status_code)
+            else:
+                logger.debug(f"URL {url} gave zero byte content reply with Status Code {r.status_code}, but empty_pages_are_a_change = True")
 
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -56,7 +56,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from selenium import webdriver
         from selenium.webdriver.chrome.options import Options as ChromeOptions

changedetectionio/processors/__init__.py

@@ -26,6 +26,8 @@ class difference_detection_processor():
 
     def call_browser(self):
         from requests.structures import CaseInsensitiveDict
+        from changedetectionio.content_fetchers.exceptions import EmptyReply
+
         # Protect against file:// access
         if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
@@ -133,8 +135,18 @@ class difference_detection_processor():
         is_binary = self.watch.is_pdf
 
         # And here we go! call the right browser with browser-specific settings
-        self.fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, self.watch.get('include_filters'),
-                    is_binary=is_binary)
+        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
+
+        self.fetcher.run(url=url,
+                         timeout=timeout,
+                         request_headers=request_headers,
+                         request_body=request_body,
+                         request_method=request_method,
+                         ignore_status_codes=ignore_status_codes,
+                         current_include_filters=self.watch.get('include_filters'),
+                         is_binary=is_binary,
+                         empty_pages_are_a_change=empty_pages_are_a_change
+                         )
 
         #@todo .quit here could go on close object, so we can run JS if change-detected
         self.fetcher.quit()

changedetectionio/templates/settings.html

@@ -76,7 +76,7 @@
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">When a page contains HTML, but no renderable text appears (empty page), is this considered a change?</span>
+                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
                     </div>
                 {% if form.requests.proxy %}
                     <div class="pure-control-group inline-radio">

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -112,7 +112,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     res = client.post(
         url_for("settings_page"),
         data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": 'triggered text was -{{triggered_text}}-',
+              "application-notification_body": 'triggered text was -{{triggered_text}}- 网站监测 内容更新了',
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
               "application-notification_urls": test_notification_url,
               "application-minutes_between_check": 180,
@@ -167,9 +167,10 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     # Takes a moment for apprise to fire
     time.sleep(3)
     assert os.path.isfile("test-datastore/notification.txt"), "Notification fired because I can see the output file"
-    with open("test-datastore/notification.txt", 'r') as f:
-        response= f.read()
-        assert '-Oh yes please-' in response
+    with open("test-datastore/notification.txt", 'rb') as f:
+        response = f.read()
+        assert b'-Oh yes please-' in response
+        assert '网站监测 内容更新了'.encode('utf-8') in response
 
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_nonrenderable_pages.py

@@ -1,12 +1,7 @@
 #!/usr/bin/env python3
 
-import time
 from flask import url_for
-from urllib.request import urlopen
-from .util import set_original_response, set_modified_response, live_server_setup
-
-sleep_time_for_fetch_thread = 3
-
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
 
 def set_nonrenderable_response():
     test_return_data = """<html>
@@ -22,6 +17,13 @@ def set_nonrenderable_response():
 
     return None
 
+def set_zero_byte_response():
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("")
+
+    return None
+
 def test_check_basic_change_detection_functionality(client, live_server, measure_memory_usage):
     set_original_response()
     live_server_setup(live_server)
@@ -35,18 +37,11 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     assert b"1 Imported" in res.data
 
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
-    # Do this a few times.. ensures we dont accidently set the status
-    for n in range(3):
-        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)
-
-        # It should report nothing found (no new 'unviewed' class)
-        res = client.get(url_for("index"))
-        assert b'unviewed' not in res.data
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
 
 
     #####################
@@ -64,7 +59,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     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)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
@@ -86,14 +81,20 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     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)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
+    client.get(url_for("mark_all_viewed"), follow_redirects=True)
 
-
-
+    # A totally zero byte (#2528) response should also not trigger an error
+    set_zero_byte_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data # A change should have registered because empty_pages_are_a_change is ON
+    assert b'fetch-error' not in res.data
 
     #
     # Cleanup everything

changedetectionio/tests/test_notification.py

@@ -291,11 +291,11 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
         data={
               "application-fetch_backend": "html_requests",
               "application-minutes_between_check": 180,
-              "application-notification_body": '{ "url" : "{{ watch_url }}", "secret": 444 }',
+              "application-notification_body": '{ "url" : "{{ watch_url }}", "secret": 444, "somebug": "网站监测 内容更新了" }',
               "application-notification_format": default_notification_format,
               "application-notification_urls": test_notification_url,
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-              "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
+              "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }} ",
               },
         follow_redirects=True
     )
@@ -324,6 +324,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
         j = json.loads(x)
         assert j['url'].startswith('http://localhost')
         assert j['secret'] == 444
+        assert j['somebug'] == '网站监测 内容更新了'
 
     # URL check, this will always be converted to lowercase
     assert os.path.isfile("test-datastore/notification-url.txt")
@@ -354,9 +355,10 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
 #2510
 def test_global_send_test_notification(client, live_server, measure_memory_usage):
 
-
     #live_server_setup(live_server)
     set_original_response()
+    if os.path.isfile("test-datastore/notification.txt"):
+        os.unlink("test-datastore/notification.txt")
 
     # otherwise other settings would have already existed from previous tests in this file
     res = client.post(
@@ -364,7 +366,8 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
         data={
             "application-fetch_backend": "html_requests",
             "application-minutes_between_check": 180,
-            "application-notification_body": 'change detection is cool',
+            #1995 UTF-8 content should be encoded
+            "application-notification_body": 'change detection is cool 网站监测 内容更新了',
             "application-notification_format": default_notification_format,
             "application-notification_urls": "",
             "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
@@ -399,8 +402,7 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
 
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
-        assert 'change detection is coo' in x
-
+        assert 'change detection is cool 网站监测 内容更新了' in x
 
     os.unlink("test-datastore/notification.txt")
 
@@ -420,7 +422,7 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
         # Should come from notification.py default handler when there is no notification body to pull from
-        assert 'change detection is coo' in x
+        assert 'change detection is cool 网站监测 内容更新了' in x
 
     client.get(
         url_for("form_delete", uuid="all"),

changedetectionio/update_worker.py

@@ -1,6 +1,5 @@
 from .processors.exceptions import ProcessorException
-from . import content_fetchers
-
+import changedetectionio.content_fetchers.exceptions as content_fetchers_exceptions
 from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio import html_tools
 
@@ -301,7 +300,7 @@ class update_worker(threading.Thread):
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.ReplyWithContentButNoText as e:
+                    except content_fetchers_exceptions.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
@@ -327,7 +326,7 @@ class update_worker(threading.Thread):
                             
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.Non200ErrorCodeReceived as e:
+                    except content_fetchers_exceptions.Non200ErrorCodeReceived as e:
                         if e.status_code == 403:
                             err_text = "Error - 403 (Access denied) received"
                         elif e.status_code == 404:
@@ -380,23 +379,23 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame as e:
+                    except content_fetchers_exceptions.checksumFromPreviousCheckWasTheSame as e:
                         # Yes fine, so nothing todo, don't continue to process.
                         process_changedetection_results = False
                         changed_detected = False
-                    except content_fetchers.exceptions.BrowserConnectError as e:
+                    except content_fetchers_exceptions.BrowserConnectError as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserFetchTimedOut as e:
+                    except content_fetchers_exceptions.BrowserFetchTimedOut as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserStepsStepException as e:
+                    except content_fetchers_exceptions.BrowserStepsStepException as e:
 
                         if not self.datastore.data['watching'].get(uuid):
                             continue
@@ -438,25 +437,25 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.EmptyReply as e:
+                    except content_fetchers_exceptions.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.ScreenshotUnavailable as e:
+                    except content_fetchers_exceptions.ScreenshotUnavailable as e:
                         err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.JSActionExceptions as e:
+                    except content_fetchers_exceptions.JSActionExceptions as e:
                         err_text = "Error running JS Actions - Page request - "+e.message
                         if e.screenshot:
                             watch.save_screenshot(screenshot=e.screenshot, as_error=True)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.PageUnloadable as e:
+                    except content_fetchers_exceptions.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
                         if e.message:
                             err_text = "{} - {}".format(err_text, e.message)
@@ -468,7 +467,7 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code,
                                                                            'has_ldjson_price_data': None})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserStepsInUnsupportedFetcher as e:
+                    except content_fetchers_exceptions.BrowserStepsInUnsupportedFetcher as e:
                         err_text = "This watch has Browser Steps configured and so it cannot run with the 'Basic fast Plaintext/HTTP Client', either remove the Browser Steps or select a Chrome fetcher."
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
                         process_changedetection_results = False