mkdocs-htmlproofer-plugin 1.1.0__tar.gz → 1.2.1__tar.gz

{mkdocs-htmlproofer-plugin-1.1.0/mkdocs_htmlproofer_plugin.egg-info → mkdocs-htmlproofer-plugin-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mkdocs-htmlproofer-plugin
-Version: 1.1.0
+Version: 1.2.1
 Summary: A MkDocs plugin that validates URL in rendered HTML files
 Home-page: https://github.com/manuzhang/mkdocs-htmlproofer-plugin
 Author: Manu Zhang
@@ -162,6 +162,17 @@ plugins:
       validate_rendered_template: True
 ```
 
+### `skip_downloads`
+
+Optionally skip downloading of a remote URLs content via GET request. This can
+considerably reduce the time taken to validate URLs.
+
+```yaml
+plugins:
+  - htmlproofer:
+      skip_downloads: True
+```
+
 ## Compatibility with `attr_list` extension
 
 If you need to manually specify anchors make use of the `attr_list` [extension](https://python-markdown.github.io/extensions/attr_list) in the markdown.

{mkdocs-htmlproofer-plugin-1.1.0 → mkdocs-htmlproofer-plugin-1.2.1}/README.md

@@ -139,6 +139,17 @@ plugins:
       validate_rendered_template: True
 ```
 
+### `skip_downloads`
+
+Optionally skip downloading of a remote URLs content via GET request. This can
+considerably reduce the time taken to validate URLs.
+
+```yaml
+plugins:
+  - htmlproofer:
+      skip_downloads: True
+```
+
 ## Compatibility with `attr_list` extension
 
 If you need to manually specify anchors make use of the `attr_list` [extension](https://python-markdown.github.io/extensions/attr_list) in the markdown.

{mkdocs-htmlproofer-plugin-1.1.0 → mkdocs-htmlproofer-plugin-1.2.1}/htmlproofer/plugin.py

@@ -65,6 +65,7 @@ class HtmlProoferPlugin(BasePlugin):
         ('raise_error', config_options.Type(bool, default=False)),
         ('raise_error_after_finish', config_options.Type(bool, default=False)),
         ('raise_error_excludes', config_options.Type(dict, default={})),
+        ('skip_downloads', config_options.Type(bool, default=False)),
         ('validate_external_urls', config_options.Type(bool, default=True)),
         ('validate_rendered_template', config_options.Type(bool, default=False)),
         ('ignore_urls', config_options.Type(list, default=[])),
@@ -115,9 +116,10 @@ class HtmlProoferPlugin(BasePlugin):
 
         all_element_ids = set(tag['id'] for tag in soup.select('[id]'))
         all_element_ids.add('')  # Empty anchor is commonly used, but not real
-        for a in soup.find_all('a', href=True):
-            url = a['href']
 
+        urls = set(a['href'] for a in soup.find_all('a', href=True)) | set(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}")
@@ -146,7 +148,13 @@ class HtmlProoferPlugin(BasePlugin):
     @lru_cache(maxsize=1000)
     def resolve_web_scheme(self, url: str) -> int:
         try:
-            response = self._session.get(url, timeout=URL_TIMEOUT)
+            response = self._session.get(url, timeout=URL_TIMEOUT, stream=True)
+
+            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):
+                    pass
+
             return response.status_code
         except requests.exceptions.Timeout:
             return 504
@@ -187,18 +195,20 @@ class HtmlProoferPlugin(BasePlugin):
             return True
 
         url_target, _, optional_anchor = match.groups()
-        _, extension = os.path.splitext(url_target)
-        if extension == ".html":
-            # URL is a link to another local Markdown file that may include an anchor.
-            target_markdown = HtmlProoferPlugin.find_target_markdown(url_target, src_path, files)
-            if target_markdown is None:
-                # The corresponding Markdown page was not found.
-                return False
-            if optional_anchor and not HtmlProoferPlugin.contains_anchor(target_markdown, optional_anchor):
-                # The corresponding Markdown header for this anchor was not found.
-                return False
-        elif HtmlProoferPlugin.find_source_file(url_target, src_path, files) is None:
+        source_file = HtmlProoferPlugin.find_source_file(url_target, src_path, files)
+        if source_file is None:
             return False
+
+        # If there's an anchor (fragment) on the link, we try to find it in the source_file
+        if optional_anchor:
+            _, extension = os.path.splitext(source_file.src_uri)
+            # Currently only Markdown-based pages are supported, but conceptually others could be added below
+            if extension == ".md":
+                if source_file.page is None or source_file.page.markdown is None:
+                    return False
+                if not HtmlProoferPlugin.contains_anchor(source_file.page.markdown, optional_anchor):
+                    return False
+
         return True
 
     @staticmethod
@@ -285,17 +295,10 @@ class HtmlProoferPlugin(BasePlugin):
     def bad_url(url_status: int) -> bool:
         if url_status == -1:
             return True
-        elif url_status == 401 or url_status == 403:
-            return False
-        elif url_status in (503, 504):
-            # Usually transient
-            return False
-        elif url_status == 999:
-            # Returned by some websites (e.g. LinkedIn) that think you're crawling them.
-            return False
         elif url_status >= 400:
             return True
-        return False
+        else:
+            return False
 
     @staticmethod
     def is_error(config: Config, url: str, url_status: int) -> bool:

{mkdocs-htmlproofer-plugin-1.1.0 → mkdocs-htmlproofer-plugin-1.2.1/mkdocs_htmlproofer_plugin.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mkdocs-htmlproofer-plugin
-Version: 1.1.0
+Version: 1.2.1
 Summary: A MkDocs plugin that validates URL in rendered HTML files
 Home-page: https://github.com/manuzhang/mkdocs-htmlproofer-plugin
 Author: Manu Zhang
@@ -162,6 +162,17 @@ plugins:
       validate_rendered_template: True
 ```
 
+### `skip_downloads`
+
+Optionally skip downloading of a remote URLs content via GET request. This can
+considerably reduce the time taken to validate URLs.
+
+```yaml
+plugins:
+  - htmlproofer:
+      skip_downloads: True
+```
+
 ## Compatibility with `attr_list` extension
 
 If you need to manually specify anchors make use of the `attr_list` [extension](https://python-markdown.github.io/extensions/attr_list) in the markdown.

{mkdocs-htmlproofer-plugin-1.1.0 → mkdocs-htmlproofer-plugin-1.2.1}/setup.py

@@ -9,7 +9,7 @@ def read(fname: str):
 
 setup(
     name='mkdocs-htmlproofer-plugin',
-    version='1.1.0',
+    version='1.2.1',
     description='A MkDocs plugin that validates URL in rendered HTML files',
     long_description=read('README.md'),
     long_description_content_type='text/markdown',