赞
踩
对于新手做Python爬虫来说是有点难处的,前期练习的时候可以直接套用模板,这样省时省力还很方便。
使用Python爬取某网站的相关数据,并保存到同目录下Excel。
直接上代码:
import re import urllib.error import urllib.request import xlwt from bs4 import BeautifulSoup def main(): baseurl ="http://jshk.com.cn" datelist = getDate(baseurl) savepath=".\\jshk.xls" saveDate(datelist,savepath) # askURL("http://jshk.com.cn/") findlink = re.compile(r'<a href="(.*?)">') findimg = re.compile(r'<img.*src="(.*?)"',re.S) findtitle = re.compile(r'<span class="title">(.*)</span') findrating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span') findjudge = re.compile(r'<span>(\d*)人评价</span>') findinq= re.compile(r'<span class="inq">(.*)</span>') def getDate(baseurl): datalist =[] for i in range(0,10): url=baseurl+str(i*25) html=askURL(url) soup = BeautifulSoup(html,"html.parser") for item in soup.find_all('div',class_="item"): data = [] item = str(item) link = re.findall(findlink,item)[0] data.append(link) img=re.findall(findimg,item)[0] data.append(img) title=re.findall(findtitle,item)[0] rating=re.findall(findrating,item)[0] data.append(rating) judge=re.findall(findjudge,item)[0] data.append(judge) inq=re.findall(findinq,item) if len(inq)!=0: inq=inq[0].replace("。","") data.append(inq) else: data.append(" ") print(data) datalist.append(data) print(datalist) return datalist def askURL(url): head = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36"} request=urllib.request.Request(url,headers=head) html="" try: response=urllib.request.urlopen(request) html=response.read().decode("utf-8") # print(html) except urllib.error.URLError as e: if hasattr(e,"code"): print(e.code) if hasattr(e,"reason"): print(e.reason) return html def saveDate(datalist,savepath): workbook = xlwt.Workbook(encoding='utf-8') worksheet = workbook.add_sheet('电影',cell_overwrite_ok=True) col =("电影详情","图片","影片","评分","评价数","概况") for i in range(0,5): worksheet.write(0,i,col[i]) for i in range(0,250): print("第%d条" %(i+1)) data=datalist[i] for j in range(0,5): worksheet.write(i+1,j,data[j]) workbook.save(savepath) if __name__ == '__main__': main() print("爬取完毕")
直接复制粘贴就行。
若要更改爬取网站,则需要更改URL以及相应的html格式(代码中的“item”)。
学好 Python 不论是就业还是做副业赚钱都不错,但要学会 Python 还是要有一个学习规划。最后大家分享一份全套的 Python 学习资料,给那些想学习 Python 的小伙伴们一点帮助!
包括:Python激活码+安装包、Python web开发,Python爬虫,Python数据分析,Python自动化测试学习等教程。带你从零基础系统性的学好Python!
声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/木道寻08/article/detail/869143
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。