本文共 1175 字，大约阅读时间需要 3 分钟。

源码：

from fake_useragent 			import UserAgentfrom lxml 						import etreeimport lxml,requestsurl="https://www.jianshu.com/c/qqfxgN?utm_campaign=haruki&utm_content=note&utm_medium=reader_share&utm_source=qq"def getHtml(url):	'''	获取网页源码	return html	'''	headers = {
   		"Host": "www.jianshu.com",		"Referer": "https://www.jianshu.com/",		"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"	}	req = requests.get(url, headers=headers)	html = etree.HTML(req.text)	return htmldef parse(html):	'''	解析网页	'''	nodes = html.xpath("//ul[@class='note-list']/li//div[@class='content']")	for node in nodes:		title = node.xpath(".//a[@class='title']/text()")[0]		nickname = node.xpath(".//div[@class='meta']/a/text()")[0]		comment = node.xpath(".//div[@class='meta']/a//text()")[2].strip()		like = node.xpath(".//div[@class='meta']/span/text()")[0].strip()		essay = {
   			"title" : title,			"nickname" : nickname,			"comment" : comment,			"like" : like		}		print("文章信息：{}".format(essay))def main():	html = getHtml(url)	parse(html)if __name__ == '__main__':	main()

有不明的地方在下方留言，我看到后会尽快回复的

转载地址：https://mtyjkh.blog.csdn.net/article/details/86819881 如侵犯您的版权，请留言回复原文章的地址，我们会给您删除此文章，给您带来不便请您谅解！