html = etree.HTML(text)
ret_list = html.xpath("xpath語法規(guī)則字符串")

import requests
from lxml import etree

class Tieba(object):

? ? def __init__(self,name):
? ? ? ? self.url = "https://tieba.baidu.com/f?ie=utf-8&kw={}".format(name)
? ? ? ? self.headers = {
? ? ? ? ? ? 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36'
? ? ? ? }

? ? def get_data(self,url):
? ? ? ? response = requests.get(url,headers=self.headers)
? ? ? ? with open("temp.html","wb") as f:
? ? ? ? ? ? f.write(response.content)

? ? ? ? return response.content

? ? def parse_data(self,data):
? ? ? ? # 創(chuàng)建element對象
? ? ? ? data = data.decode().replace("<!--","").replace("-->","")
? ? ? ? html =etree.HTML(data)

? ? ? ? el_list = html.xpath('//li[@class="j_thread_list clearfix"]/div/div[2]/div[1]/div[1]/a')
? ? ? ? #print(len(el_list))

? ? ? ? data_list = []

? ? ? ? for el in el_list:
? ? ? ? ? ? temp = {}
? ? ? ? ? ? temp['title'] = el.xpath("./text()")[0]
? ? ? ? ? ? temp['link'] = 'http://tieba.baidu.com' + el.xpath("./@href")[0]
? ? ? ? ? ? data_list.append(temp)

? ? ? ? # 獲取下一頁url
? ? ? ? try:
? ? ? ? ? ? next_url = 'https:' + html.xpath('//a[contains(text(),"下一頁"]/@href')[0]
? ? ? ? except:
? ? ? ? ? ? next_url = None

? ? ? ? return data_list,next_url

? ? def save_data(self,data_list):
? ? ? ? for data in data_list:
? ? ? ? ? ? print(data)

? ? def run(self):
? ? ? ? # url
? ? ? ? # headers
? ? ? ? next_url = self.url

? ? ? ? while True:

? ? ? ? ? ? # 發(fā)送請求，獲取響應
? ? ? ? ? ? data = self.get_data(self.url)
? ? ? ? ? ? # 從響應中提取數(shù)據(jù)（數(shù)據(jù)和翻頁用的url)
? ? ? ? ? ? data_list,next_url = self.parse_data(data)

? ? ? ? ? ? self.save_data(data_list)

? ? ? ? ? ? print(next_url)

? ? ? ? ? ? # 判斷是否終結(jié)
? ? ? ? ? ? if next_url == None:
? ? ? ? ? ? ? ? break

if __name__ == '__main__':
? ? tieba =Tieba("傳智播客")
? ? tieba.run()

from lxml import etree

html_str = """<div<<ul>
? ? ? ? <li class="item-1"><a href="link1.html" rel="external nofollow" >first item</a></li>
? ? ? ? <li class="item-1"><a href="link2.html" rel="external nofollow" >second item</a></li>
? ? ? ? <li class="item-inactive"><a href="link3.html" rel="external nofollow" >third item</a></li>
? ? ? ? <li class="item-1"><a href="link4.html" rel="external nofollow" >fourth item</a></li>
? ? ? ? <li class="item=0"><a href="link5.html" rel="external nofollow" >fifth item</a>
? ? ? ? </ur></div>
"""

html = etree.HTML(html_str)

handeled_html_str = etree.tostring(html).decode()
print(handeled_html_str)