爬虫代码模版

最新推荐文章于 2024-08-02 10:29:40 发布

m0_69163544

最新推荐文章于 2024-08-02 10:29:40 发布

阅读量149

点赞数

文章标签：爬虫

本文链接：https://blog.csdn.net/m0_69163544/article/details/125605915

版权

from bs4 import BeautifulSoup
import urllib.request,urllib.error
import ssl
import re
import xlwt
def main():
    baseurl = "http://ylbz.yn.gov.cn/index.php?s=form&c=ybypml&m=page"
    datalist=getDate(baseurl)
    print(datalist)
    savapath = "医保药品目录爬取.xls"
    saveData(datalist,savapath)
finddata= re.compile(r'<td>(.*?)</td>')
def askURL(url):
    head = {
        "User-Agent": "Mozilla / 5.0(Macintosh;IntelMacOSX10_15_7) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 100.0.4896.60Safari / 537.36"
    }
    #模拟浏览器访问
    req = urllib.request.Request(url, headers=head)
    res = urllib.request.urlopen(req, context=ssl.SSLContext(ssl.PROTOCOL_SSLv23))
    #加个证书
    html = res.read().decode("utf-8")
    return html

def getDate(baseurl):
    alldata=[]
    for i in range(1,11):
        url=baseurl+"&page="+str(i)
        html=askURL(url)
        soup=BeautifulSoup(html,"html.parser")
        #创建Beautifulsoup对象来分析文档
        for item in soup.find_all("td"):
                item=str(item)
                data=re.findall(finddata,item)
                alldata.append(data)
            #爬取网站前十页内容
    return alldata

def saveData(datalist,savepath):
    #将数据保存到excel
    book = xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet=book.add_sheet('医保药品',cell_overwrite_ok=True)
    col =("药品编码","通用名","商品名","类别","规格","包装","剂型","厂家")
    for i in range(0,8):
        sheet.write(0,i,col[i])#列名
    for j in range(0,250):
         for r in range(0,8):
            data=datalist[j*8+r]
            sheet.write(j+1,r,data)
    book.save(savepath)


if __name__ == '__main__':
    main()