豆瓣爬出Top250的数据，学习记录。

#-*- codeing = utf-8 -*-
#@Time : 2020/6/3 23:09
#@Author : Matthew
#@File : 爬虫.py
#@Software : PyCharmfrom bs4 import BeautifulSoup  #网页解析，获取数据
import  re                     #正则表达式，匹配文字
import urllib.request,urllib.error  #指定URL，获取网页数据
import xlwt                         #进行excel操作
import sqlite3                      #进行SQLite数据库操作def  main():baseurl ="https://movie.douban.com/top250?start="#1.爬取网页dataList = getData(baseurl)#2.解析数据#3.保存数据savePath = "豆瓣电影Top250.xls"saveData(savePath,dataList)askURL(baseurl)#影片详情链接
findlink = re.compile(r'<a href="(.*?)">')  #生成正则表达式对象，表示规则
#影片图片链接
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)  #忽略换行符
#影片片名
findTitle = re.compile(r'<span class="title">(.*)</span>')
#影片的评分
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
#评价人数
findNumber = re.compile(r'<span>(\d*)人评价</span>')
#影片概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
#影片相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)# 1.爬取网页
def  getData(baseurl):dataList = []for i in range(0,10): #反复调用获取top250 10*25url = baseurl +str(i*25)html = askURL(url)      #获取网页数据#2.解析数据soup = BeautifulSoup(html,"html.parser") #解析html 用html解析器 soup是树形结构for item in soup.find_all('div',class_="item"):              #查找符合的数据，形成列表data = []#保存一部电影的信息item = str(item)#link 影片详情链接link = re.findall(findlink,item)[0]   #通过正则表达式查找指定的字符串data.append(link)                       #详情链接imgSrc = re.findall(findImgSrc,item)[0]data.append(imgSrc)                     #图片链接titles = re.findall(findTitle,item)if(len(titles)==2):chinesTitle = titles[0]             #中文名字data.append(chinesTitle)otherTitle = titles[1].replace("/","")  #去掉/data.append(otherTitle)             #外文名字else:data.append(titles[0])data.append(" ")                    #外文名字留空rating = re.findall(findRating,item)[0]data.append(rating)                     #评分number = re.findall(findNumber,item)[0]data.append(number)                    #人数inq = re.findall(findInq,item)if len(inq)!=0:inq = inq[0].replace("。","")data.append(inq)                       #概述else:data.append(" ")bd = re.findall(findBd,item)[0]bd = re.sub('<br(\s+)?/>(/s+)?'," ",bd)  #去掉<br/>bd = re.sub('/'," ",bd)bd = re.sub(r'\n'," ",bd)data.append(bd.strip())                #strip去掉空格dataList.append(data)                 #将一部电影内容放入datalist中return dataList#3.保存数据
def saveData(savePath,dataList):print("save...")book = xlwt.Workbook(encoding="utf-8",style_compression=0)sheet = book.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)col = ("电影详情链接","图片链接","影片中文名","影片外文名","影片评分","观看人数","影片概述","相关信息")for i in range(0,8):sheet.write(0,i,col[i])  #写入列名for i in range(0,len(dataList)):for j in range(0,len(dataList[i])):sheet.write(i+1,j,dataList[i][j])book.save(savePath)        #保存数据print("Saving Over")
#得到指定一个url网页的内容def askURL(url):#伪装一个浏览器 用户代理告诉服务器我们是什么类型的机器、浏览器 模拟一个头部head = {r"User-Agent":r"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36"}req= urllib.request.Request(url,headers=head)html =""try:response = urllib.request.urlopen(req)html = response.read().decode()#  print(html)except urllib.error.URLError as e:if hasattr(e,"code"):print(e.code)if hasattr(e,"reason"):print(e.reason)return htmlif __name__ =="__main__"   : # main 函数入口main()