Python使用BeautifulSoup4修改网页内容的实战记录

    < img src=\"图片地址_compressed.jpg\" data-zy-media-id=\"图片地址.jpg\">
    

pip install bs4
pip install lxml

import os
from bs4 import BeautifulSoup
htmlstr=\'\' \\
        \'\' \\
        \'\' \\
        \'\' \\
        \'\' \\
        \'\' \\
        \'\' \\
        \'\' \\
        \'\' \\
        \'\'

def procHtml(htmlstr):
    soup = BeautifulSoup(htmlstr, \'lxml\')
    a_tags=soup.select(\'a\')
    for a_tag in a_tags:
        a_tag_src = a_tag.get(\'href\')
        a_tag_filename = os.path.basename(a_tag_src)
        a_tag_path = os.path.join(\'src\', a_tag_filename)
        a_tag[\'href\']=a_tag_path
        next_tag=a_tag.next
        #判断是视频还是图片，如果a标签带了class=\"videoslide\" 是视频否则是图片
        if a_tag.get(\'class\') and \'videoslide\'==a_tag.get(\'class\')[0]:
            # 处理视频文件
            media_id = next_tag.get(\'data-zy-media-id\')
            if media_id:
                media_url = \'http://www.test.com/travel/show_media/\' + str(media_id)+\'.mp4\'
                media_filename = os.path.basename(media_url)
                media_path = os.path.join(\'src\', media_filename)
                # 将div.video标签替换a标签
                video_html = \'
\'
                video_soup = BeautifulSoup(video_html, \'lxml\')
                a_tag.replaceWith(video_soup.div)
        else:
            #获取图片信息
            if \'img\'==next_tag.name:
                img_src=next_tag.get(\'src\')
                # 判断是否路径是否为本地资源 data:image和file:
                if img_src.find(\'data:image\') == -1 and img_src.find(\'file:\') == -1:
                    img_filename = os.path.basename(img_src)
                    img_path = os.path.join(\'src\', img_filename)
                    # 将
标签替换a标签
                    figcaption=\'\'
                    figure_html=\'
\'
                    figure_soup = BeautifulSoup(figure_html, \'lxml\')
                    a_tag.replaceWith(figure_soup.figure)
    html_content = soup.contents[0]
    return html_content

if __name__ == \'__main__\':
    pro_html_str=procHtml(htmlstr)
    print(pro_html_str)