学爬虫的时候无聊练练手
主要用到xpath作为解析网页标签的工具
接下来没啥好说的了
就是简单的爬虫
import requests
from lxml import etree
head = {}
url = "http://top.baidu.com/buzz?b=341&fr=topindex"
head["User-Agent"] = "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:63.0) Gecko/20100101 Firefox/63.0"
head["Accept"]= "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
head["Accept-Language"]= "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2"
head["Connection"] = "keep-alive"
def main():
print("百度热搜top10: ")
res = requests.get(url , headers = head)
with open("html.txt", "wb") as f:
f.write(res.content)
html = etree.parse('html.txt' , etree.HTMLParser(encoding='gbk'))
top_list = html.xpath('//a[@class="list-title"]/text()')
num_search = html.xpath('//span[@class="icon-rise"]/text()')
for i , j in zip(top_list[:10] , num_search[:10]):
print(i ,"搜索指数为:" , j )
if __name__ == '__main__':
main()