fixed conflicts

getnikola · Jun 6, 2017 · de8d483596401d8c6c53db1c757707f637ff3119 · de8d483
2 parents 8ba4937 + 156277a
commit de8d483596401d8c6c53db1c757707f637ff3119
Unified Split

Showing with 57 additions and 2 deletions.

+1 −0 CHANGES.txt

+26 −0 docs/manual.txt

+30 −2 nikola/plugins/compile/html.py
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -6,6 +6,7 @@ Features
 
 * New METADATA_FORMAT option to choose preferred metadata format 
   (Nikola/YAML/TOML/Pelican) (Part of Issue #2801)
+* Extract metadata from HTML meta and title tags like Pelican (Issue #1923)
 
 New in v7.8.7
 =============

diff --git a/docs/manual.txt b/docs/manual.txt
@@ -418,6 +418,7 @@ other static site generators. The currently supported metadata formats are:
 * TOML, between ``+++`` (Hugo)
 * reST docinfo (Pelican)
 * Markdown metadata extension (Pelican)
+* HTML meta tags (Pelican)
 
 You can add arbitrary meta fields in any format.
 
@@ -537,6 +538,30 @@ the `markdown metadata extension docs. <https://pythonhosted.org/Markdown/extens
 
 Note that keys are converted to lowercase automatically.
 
+HTML meta tags
+``````````````
+
+For HTML source files, metadata will be extracted from ``meta`` tags, and the title from the ``title`` tag.
+Following Pelican's behaviour, tags can be put in a "tags" meta tag or in a "keywords" meta tag. Example:
+
+.. code:: html
+
+    <html>
+        <head>
+            <title>My super title</title>
+            <meta name="tags" content="thats, awesome" />
+            <meta name="date" content="2012-07-09 22:28" />
+            <meta name="modified" content="2012-07-10 20:14" />
+            <meta name="category" content="yeah" />
+            <meta name="authors" content="Conan Doyle" />
+            <meta name="summary" content="Short version for index and feeds" />
+        </head>
+        <body>
+            This is the content of my super blog post.
+        </body>
+    </html>
+
+
 Mapping metadata from other formats
 ```````````````````````````````````
 
@@ -549,6 +574,7 @@ For Pelican, use:
     METADATA_MAPPING = {
         "rest_docinfo": {"summary": "description", "modified": "updated"},
         "markdown_metadata": {"summary": "description", "modified": "updated"}
+        "html_metadata": {"summary": "description", "modified": "updated"}
     }
 
 For Hugo, use:

diff --git a/nikola/plugins/compile/html.py b/nikola/plugins/compile/html.py
@@ -28,12 +28,14 @@
 
 from __future__ import unicode_literals
 
-import os
 import io
+import os
+
+import lxml.html
 
 from nikola import shortcodes as sc
 from nikola.plugin_categories import PageCompiler
-from nikola.utils import makedirs, write_metadata
+from nikola.utils import LocaleBorg, makedirs, map_metadata, write_metadata
 
 
 class CompileHtml(PageCompiler):
@@ -84,3 +86,29 @@ def create_post(self, path, **kw):
                 fd.write(write_metadata(metadata))
                 fd.write('-->\n\n')
             fd.write(content)
+
+    def read_metadata(self, post, file_metadata_regexp=None, unslugify_titles=False, lang=None):
+        """Read the metadata from a post's meta tags, and return a metadata dict."""
+        if lang is None:
+            lang = LocaleBorg().current_lang
+        source_path = post.translated_source_path(lang)
+
+        with io.open(source_path, 'r', encoding='utf-8') as inf:
+            data = inf.read()
+
+        metadata = {}
+        doc = lxml.html.document_fromstring(data)
+        title_tag = doc.find('*//title')
+        if title_tag is not None:
+            metadata['title'] = title_tag.text
+        meta_tags = doc.findall('*//meta')
+        for tag in meta_tags:
+            k = tag.get('name').lower()
+            if not k:
+                continue
+            elif k == 'keywords':
+                k = 'tags'
+            metadata[k] = tag.get('content', '')
+        map_metadata(metadata, 'html_metadata', self.site.config)
+        return metadata
+