collect.py 文件源码

def get_child_urls(main_page, max_child=20):
    """retrieve urls from giving html page.
    args:
        main_page(str): html file.
        max_child(int): max number of return urls.
    return:
        list of url string.
    """
    from bs4 import BeautifulSoup, SoupStrainer
    children = []
    for link in BeautifulSoup(main_page,
                              "html.parser",
                              parse_only=SoupStrainer('a')):
        if link.has_attr('href') and link['href'].startswith("http"):
            children.append(link['href'])
    if len(children) > max_child:
        children = children[:max_child]
    return children