def get_content_and_images(page_tree, div_name, div_classes):
content = ''
img_href_list = []
for div_class in div_classes:
# 获取内容和图片/视频链接
new_content = ''.join(page_tree.xpath(f'//{div_name}[contains(@class, "{div_class}")]//p//text()'))
new_img_href_list = page_tree.xpath(
f"//{div_name}[contains(@class, '{div_class}')]//a[contains(@href,'.docx')]/@href | "
f"//{div_name}[contains(@class, '{div_class}')]//a[contains(@href,'.doc')]/@href | "
f"//{div_name}[contains(@class, '{div_class}')]//a[contains(@href,'.xlsx')]/@href | "
f"//{div_name}[contains(@class, '{div_class}')]//a[contains(@href,'.xls')]/@href | "
f"//{div_name}[contains(@class, '{div_class}')]//a[contains(@href,'.pdf')]/@href | "
f"//{div_name}[contains(@class, '{div_class}')]//a[contains(@href,'.zip')]/@href | "
f"//{div_name}[contains(@class, '{div_class}')]//img[contains(@src,'.jpg')]/@src | "
f"//{div_name}[contains(@class, '{div_class}')]//img[contains(@src,'.png')]/@src"
)
# # 如果已经有内容则跳出循环
if new_content!='' or new_img_href_list!=[]:
content = new_content
img_href_list = new_img_href_list
break
return content, img_href_list
div_name = 'div'
div_classes = ['xinagxizhengwen']
content, img_href_list = get_content_and_images(page_tree, div_name, div_classes)
标签：提取,name,img,contains,链接,href,文章,div,class From： https://www.cnblogs.com/wolvies/p/18382832