Python学习之路-爬虫（百度&微博热搜）

两段程序，在前辈基础上略有改动

百度热搜Top50

百度解析内容时，主要是有个序号和热度的样式各有两种

#百度热搜TOP50
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(count):
    print("百度热搜top",count,":")
    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'))
    index_list = htm