python爬取微博热搜

目录

代码

部分结果

参考文献

---

你需要修改的是代码中的"User-Agent"、"Cookie"

代码

# -*- codeing = utf-8 -*-
# @Time :  2021/11/29 13:47
# @Author : My_progress1
# @File ： 微博热播50.py
# @Software : PyCharm

import urllib.request
from bs4 import BeautifulSoup
import re
import random
import time
import urllib.request,urllib.error
import xlwt

def main():
    #1.数据抓取
    url = 'https://s.weibo.com/top/summary'
    savepath=".\\微博50.xls"
    datalist = getData(url)
    saveData(datalist,savepath)

#得到指定一个URL的网页内容
def askUrl(url):
    headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36',
            'Cookie':'login_sid_t=279de679455657cacb79ec4065a0904e; cross_origin_proto=SSL; Apache=1190887741059.4321.1637751563454; SINAGLOBAL=1190887741059.4321.1637751563454; _s_tentry=passport.weibo.com; ULV=1637751563457:1:1:1:1190887741059.4321.1637751563454:; WBtopGlobal_register_version=2021112818; webim_unReadCount=%7B%22time%22%3A1638100408403%2C%22dm_pub_total%22%3A4%2C%22chat_group_client%22%3A0%2C%22chat_group_notice%22%3A0%2C%22allcountNum%22%3A8%2C%22msgbox%22%3A0%7D; UOR=,,www.baidu.com; SUB=_2A25MoNiWDeRhGeNP6VoX8SrFzjiIHXVv1E1erDV8PUNbmtAKLW3akW9NToltBT0K5O16dRj_Sap_RIllhgDAGM7Y; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9W5QUz5lMFNL6ksJ_NuE.B3e5JpX5KzhUgL.Fo-peonceKB4SKB2dJLoIpB4gFH8SCHWSFHFeCH81FHWxbHWx5tt; ALF=1669717061; SSOLoginState=1638181062'
                     }
    request = urllib.request.Request(url, headers=headers)
    html = ""
    response = urllib.request.urlopen(request)
    html = response.read().decode("utf-8")
    return html
#print(response.text)


findnum=re.compile(r'<td class="td-01 ranktop">(.*?)</td>', re.S)

findhot=re.compile(r'<span>(.*?)</span>', re.S)

findcomment=re.compile(r'target="_blank">(.*?)</a>',re.S)

findstyle=re.compile(r'<i class="icon-txt" style="background-color:#ff3852">(.*)</i>',re.S)

#保存数据
def getData(baseuel):
    datalist = []
    html=askUrl(baseuel)
    soup = BeautifulSoup(html, "html.parser")
    for item in soup.find_all('tr',class_=""):
        data = []
        item = str(item)
        try:
            num = re.findall(findnum,item)
            if len(num)==0:
                continue
            else:
                num=num[0]
            print("正在爬取第",num,"条")
            data.append(num)
            comment = re.findall(findcomment, item)[0]
            data.append(comment)
            hot = re.findall(findhot,item)[0]
            hot = hot.replace(" ","")
            data.append(hot)
            style = re.findall(findstyle,item)
            if len(style)==0:
                style=" "
                data.append(style)
            else:
                style=style[0]
                data.append(style)


        except (IndexError,AttributeError) as e:
            if hasattr(e, "code"):
                print(e.code)
            if hasattr(e, "reason"):
                print(e.reason)
        a = random.random()
        time.sleep(1 + 0.5 * a)
        datalist.append(data)
    return datalist

def saveData(datalist,savepath):
    book=xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet = book.add_sheet('weibo',cell_overwrite_ok=True)
    col = ('编号',"题目","热度","性质")
    for i in range(0,4):
        sheet.write(0,i,col[i])
    for i in  range(0,50):
        data = datalist[i]
        for j in range(0,4):
            sheet.write(i+1,j,data[j])
    book.save(savepath)
    print("save..")



#这也是一个判断语句，上面就是函数，下面才是程序的运行次序==次序
if __name__ == "__main__":
    main()
    print("爬取完毕")

---

部分结果

---

参考文献

Python爬虫编程基础5天速成（2021全新合集）Python入门+数据分析_哔哩哔哩_bilibili