pytextrank_textrank_scoring.py 文件源码

def markdown_preprocess(markdown_content):
    readme_rendered = mistune.markdown(markdown_content, escape=False)
    soup = BeautifulSoup(readme_rendered, "html.parser")
    # Replace anchors with content where relevant and extract otherwise
    for link in soup.findAll('a'):
        if link.text.startswith('http'):
            link.extract()
        else:
            link.replaceWithChildren()
    # Remove all the images
    for image in soup.findAll('img'):
        image.extract()
    # Remove all the code blocks
    for code_block in soup.findAll('code'):
        code_block.extract()
    return soup.text