Python获取百度热搜的完整代码

from lxml import etree
from lxml import html
import requests

headers={'User-Agent':'Mozilla/5.0 (windows NT 6.1) AppleWEBKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.63 Safari/537.36'}
page = requests.get("https://www.baidu.com",headers=headers)
html = page.text
#print(source1)
# 从字符串解析
element = etree.HTML(html)

# 元素列表，获取的方式列出了如下两种
# ps = element.xpath('//*[@id="hotsearch-content-wrapper"]/li/a/span[2]')
ps = element.xpath('//*[@class="title-content-title"]')

#热搜文本内容
text = []
if len(ps) > 0:
  for p in ps:
    #输出节点的文本
    text1 = p.text
    text.append(text1)
else:
  print("空")
  
x = element.xpath('//*[@class="s-hotsearch-content"]/li')

#热搜文本对应的排名
index = []
for x1 in x:
  #获取节点的属性
  index1 = x1.get("data-index")
  index.append(index1)

print(text)  
print(index)

#定义一个对文本和排名进行匹配的函数，返回一个字典型数据
def PP(index_array,text_array):
  x = {}
  i = 0
  for index_a in index_array:
    #index_a = int(index_a)
    
    x[index_a] = text_array[i]
    i = i + 1
  return x

re_text = PP(index,text)
#对字典性数据按key进行排序，即key=lambda re:re[0]，排序完成后再转换为字典型数据
last_text = dict(sorted(re_text.items(),key=lambda re:re[0]))