mkdocs-htmlproofer-plugin 1.2.1__tar.gz → 1.4.0__tar.gz

{mkdocs-htmlproofer-plugin-1.2.1 → mkdocs_htmlproofer_plugin-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: mkdocs-htmlproofer-plugin
-Version: 1.2.1
+Version: 1.4.0
 Summary: A MkDocs plugin that validates URL in rendered HTML files
 Home-page: https://github.com/manuzhang/mkdocs-htmlproofer-plugin
 Author: Manu Zhang
@@ -20,6 +20,22 @@ Classifier: Programming Language :: Python :: 3.11
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
+Requires-Dist: mkdocs>=1.4.0
+Requires-Dist: Markdown
+Requires-Dist: requests
+Requires-Dist: beautifulsoup4
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # mkdocs-htmlproofer-plugin [![PyPI - Version](https://img.shields.io/pypi/v/mkdocs-htmlproofer-plugin.svg)](https://pypi.org/project/mkdocs-htmlproofer-plugin)
 
@@ -27,6 +43,8 @@ License-File: LICENSE.md
 
 *A [MkDocs](https://www.mkdocs.org/) plugin that validates URLs, including anchors, in rendered html files*.
 
+> Note: [MkDocs 1.6+ supports native validation of anchors](https://www.mkdocs.org/user-guide/configuration/#validation).
+
 ## Installation
 
 0. Prerequisites
@@ -140,6 +158,21 @@ plugins:
       warn_on_ignored_urls: true
 ```
 
+### `ignore_pages`
+
+Avoid validating the URLs on the given list of markdown pages by ignoring them altogether.
+Each page in the list supports unix style wildcards `*`, `[]`, `?`, etc.
+
+```yaml
+plugins:
+  - search
+  - htmlproofer:
+      raise_error: True
+      ignore_pages:
+        - path/to/file
+        - path/to/folder/*
+```
+
 ### `validate_external_urls`
 
 Avoids validating any external URLs (i.e those starting with http:// or https://).

{mkdocs-htmlproofer-plugin-1.2.1 → mkdocs_htmlproofer_plugin-1.4.0}/README.md

@@ -4,6 +4,8 @@
 
 *A [MkDocs](https://www.mkdocs.org/) plugin that validates URLs, including anchors, in rendered html files*.
 
+> Note: [MkDocs 1.6+ supports native validation of anchors](https://www.mkdocs.org/user-guide/configuration/#validation).
+
 ## Installation
 
 0. Prerequisites
@@ -117,6 +119,21 @@ plugins:
       warn_on_ignored_urls: true
 ```
 
+### `ignore_pages`
+
+Avoid validating the URLs on the given list of markdown pages by ignoring them altogether.
+Each page in the list supports unix style wildcards `*`, `[]`, `?`, etc.
+
+```yaml
+plugins:
+  - search
+  - htmlproofer:
+      raise_error: True
+      ignore_pages:
+        - path/to/file
+        - path/to/folder/*
+```
+
 ### `validate_external_urls`
 
 Avoids validating any external URLs (i.e those starting with http:// or https://).

{mkdocs-htmlproofer-plugin-1.2.1 → mkdocs_htmlproofer_plugin-1.4.0}/htmlproofer/plugin.py

@@ -3,6 +3,7 @@ from functools import lru_cache, partial
 import os.path
 import pathlib
 import re
+import time
 from typing import Dict, List, Optional, Set
 import urllib.parse
 import uuid
@@ -70,6 +71,8 @@ class HtmlProoferPlugin(BasePlugin):
         ('validate_rendered_template', config_options.Type(bool, default=False)),
         ('ignore_urls', config_options.Type(list, default=[])),
         ('warn_on_ignored_urls', config_options.Type(bool, default=False)),
+        ('ignore_pages', config_options.Type(list, default=[])),
+        ('retry_max_times', config_options.Type(int, default=0)),
     )
 
     def __init__(self):
@@ -112,21 +115,26 @@ class HtmlProoferPlugin(BasePlugin):
         strainer = SoupStrainer(('a', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'li', 'sup', 'img'))
 
         content = output_content if self.config['validate_rendered_template'] else page.content
-        soup = BeautifulSoup(content, 'html.parser', parse_only=strainer)
+        soup = BeautifulSoup(str(content), 'html.parser', parse_only=strainer)
 
-        all_element_ids = set(tag['id'] for tag in soup.select('[id]'))
+        all_element_ids = set(str(tag['id']) for tag in soup.select('[id]'))
         all_element_ids.add('')  # Empty anchor is commonly used, but not real
 
-        urls = set(a['href'] for a in soup.find_all('a', href=True)) | set(img['src'] for img in soup.find_all('img'))
+        urls = (set(str(a['href']) for a in soup.find_all('a', href=True)) |
+                set(str(img['src']) for img in soup.find_all('img')))
 
         for url in urls:
             if any(fnmatch.fnmatch(url, ignore_url) for ignore_url in self.config['ignore_urls']):
                 if self.config['warn_on_ignored_urls']:
                     log_warning(f"ignoring URL {url} from {page.file.src_path}")
+            elif any(
+                fnmatch.fnmatch(page.file.src_path, ignore_page)
+                for ignore_page in self.config['ignore_pages']
+            ):
+                if self.config['warn_on_ignored_urls']:
+                    log_warning(f"ignoring URL {url} from {page.file.src_path}")
             else:
-                url_status = self.get_url_status(url, page.file.src_path, all_element_ids, opt_files)
-                if self.bad_url(url_status) and self.is_error(self.config, url, url_status):
-                    self.report_invalid_url(url, url_status, page.file.src_path)
+                self.check_url(url, page.file.src_path, all_element_ids, opt_files)
 
     def report_invalid_url(self, url, url_status, src_path):
         error = f'invalid url - {url} [{url_status}] [{src_path}]'
@@ -152,7 +160,7 @@ class HtmlProoferPlugin(BasePlugin):
 
             if self.config['skip_downloads'] is False:
                 # Download the entire contents as to not break previous behaviour.
-                for _ in response.iter_content(chunk_size=1024):
+                for _ in response.iter_content(chunk_size=1024 * 1024):
                     pass
 
             return response.status_code
@@ -163,6 +171,27 @@ class HtmlProoferPlugin(BasePlugin):
         except requests.exceptions.ConnectionError:
             return -1
 
+    def check_url(
+            self,
+            url: str,
+            src_path: str,
+            all_element_ids: Set[str],
+            files: Dict[str, File],
+            ) -> None:
+        retry_times = 0
+        retry_max_times = self.config['retry_max_times']
+        retry_duration = 2
+        while retry_times <= retry_max_times:
+            url_status = self.get_url_status(url, src_path, all_element_ids, files)
+            retry_times += 1
+            if self.bad_url(url_status) and self.is_error(self.config, url, url_status):
+                if retry_times > retry_max_times:
+                    self.report_invalid_url(url, url_status, src_path)
+                else:
+                    log_info(f"Retrying URL {url} from {src_path} after {retry_duration} seconds...")
+                    time.sleep(retry_duration)
+                    retry_duration *= 2
+
     def get_url_status(
             self,
             url: str,

{mkdocs-htmlproofer-plugin-1.2.1 → mkdocs_htmlproofer_plugin-1.4.0}/mkdocs_htmlproofer_plugin.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: mkdocs-htmlproofer-plugin
-Version: 1.2.1
+Version: 1.4.0
 Summary: A MkDocs plugin that validates URL in rendered HTML files
 Home-page: https://github.com/manuzhang/mkdocs-htmlproofer-plugin
 Author: Manu Zhang
@@ -20,6 +20,22 @@ Classifier: Programming Language :: Python :: 3.11
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
+Requires-Dist: mkdocs>=1.4.0
+Requires-Dist: Markdown
+Requires-Dist: requests
+Requires-Dist: beautifulsoup4
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # mkdocs-htmlproofer-plugin [![PyPI - Version](https://img.shields.io/pypi/v/mkdocs-htmlproofer-plugin.svg)](https://pypi.org/project/mkdocs-htmlproofer-plugin)
 
@@ -27,6 +43,8 @@ License-File: LICENSE.md
 
 *A [MkDocs](https://www.mkdocs.org/) plugin that validates URLs, including anchors, in rendered html files*.
 
+> Note: [MkDocs 1.6+ supports native validation of anchors](https://www.mkdocs.org/user-guide/configuration/#validation).
+
 ## Installation
 
 0. Prerequisites
@@ -140,6 +158,21 @@ plugins:
       warn_on_ignored_urls: true
 ```
 
+### `ignore_pages`
+
+Avoid validating the URLs on the given list of markdown pages by ignoring them altogether.
+Each page in the list supports unix style wildcards `*`, `[]`, `?`, etc.
+
+```yaml
+plugins:
+  - search
+  - htmlproofer:
+      raise_error: True
+      ignore_pages:
+        - path/to/file
+        - path/to/folder/*
+```
+
 ### `validate_external_urls`
 
 Avoids validating any external URLs (i.e those starting with http:// or https://).

{mkdocs-htmlproofer-plugin-1.2.1 → mkdocs_htmlproofer_plugin-1.4.0}/setup.py

@@ -9,7 +9,7 @@ def read(fname: str):
 
 setup(
     name='mkdocs-htmlproofer-plugin',
-    version='1.2.1',
+    version='1.4.0',
     description='A MkDocs plugin that validates URL in rendered HTML files',
     long_description=read('README.md'),
     long_description_content_type='text/markdown',