Method blog_add_posts

web/pandas_web.py:94–158

Given the blog feed defined in the configuration yaml, this context preprocessor fetches the posts in the feeds, and returns the relevant information for them (sorted from newest to oldest).

(context)

    @staticmethod
    def blog_add_posts(context):
        """
        Given the blog feed defined in the configuration yaml, this context
        preprocessor fetches the posts in the feeds, and returns the relevant
        information for them (sorted from newest to oldest).
        """
        tag_expr = re.compile("<.*?>")
        posts = []
        # posts from the file system
        if context["blog"]["posts_path"]:
            posts_path = context["source_path"] / context["blog"]["posts_path"]
            for fname in posts_path.iterdir():
                if fname.name.startswith("index."):
                    continue
                link = f"/{context['blog']['posts_path']}/{fname.stem}.html"
                md = markdown.Markdown(
                    extensions=context["main"]["markdown_extensions"]
                )
                with fname.open(encoding="utf-8") as f:
                    html = md.convert(f.read())
                title = md.Meta["title"][0]
                summary = re.sub(tag_expr, "", html)
                try:
                    body_position = summary.index(title) + len(title)
                except ValueError as err:
                    raise ValueError(
                        f'Blog post "{fname}" should have a markdown header '
                        f'corresponding to its "Title" element "{title}"'
                    ) from err
                summary = " ".join(summary[body_position:].split(" ")[:30])
                posts.append(
                    {
                        "title": title,
                        "author": context["blog"]["author"],
                        "published": datetime.datetime.strptime(
                            md.Meta["date"][0], "%Y-%m-%d"
                        ),
                        "feed": context["blog"]["feed_name"],
                        "link": link,
                        "description": summary,
                        "summary": summary,
                    }
                )
        # posts from rss feeds
        for feed_url in context["blog"]["feed"]:
            feed_data = feedparser.parse(feed_url)
            for entry in feed_data.entries:
                published = datetime.datetime.fromtimestamp(
                    time.mktime(entry.published_parsed)
                )
                summary = re.sub(tag_expr, "", entry.summary)
                posts.append(
                    {
                        "title": entry.title,
                        "author": entry.author,
                        "published": published,
                        "feed": feed_data["feed"]["title"],
                        "link": entry.link,