#-*- codeing = utf-8 -*-
from bs4 import BeautifulSoup #网页解析,获取数据
import re #正则表达式,进行文字匹配
import urllib.request,urllib.error #制定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)
savepath = "豆瓣电影Top250.xls"
#3.保存数据
# saveData(datalist,savepath)
#askURL("https://movie.douban.com/top250?start=")
findLink=re.compile(r'<a href="(.*?)">') #创建正则表达式对象,标售规则 影片详情链接的规则
findImgSrc=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>')
findBd=re.compile(r'<p class="">(.*?)</p>',re.S)
#爬取网页
def getData(baseurl):
datalist = []
for i in range(0,10): #调用获取页面信息的函数,10次
url = baseurl + str(i*25)
html = askURL(url) #保存获取到的网页源码
# 2.逐一解析数据
soup=BeautifulSoup(html,"html.parser")
for item in soup.find_all('div',class_="item"): #查找符合要求的字符串
# print(item)
data=[] #保存一部电影所有信息
item=str(item)
link=re.findall(findLink,item)[0] #通过正则表达式查找
data.append(link)
imgSrc=re.findall(findImgSrc, item)[0]
data.append(imgSrc)
titles=re.findall(findTitle, item)
if(len(titles)==2):
ctitle=titles[0]
data.append(ctitle)
otitle=titles[1].replace("/","")
data.append(otitle)
else:
data.append(titles[0])
data.append(' ')
rating=re.findall(findRating, item)[0]
data.append(rating)
judgeNum=re.findall(findJudge, item)[0]
data.append(judgeNum)
inq=re.findall(findInq, item)
if len(inq)!=0:
inq=inq[0].replace("。","")
data.append(inq)
else:
data.append(" ")
bd=re.findall(findBd,item)[0]
bd=re.sub('<br(\s+)?/>(\s+)?',"",bd)
bd=re.sub('/',"",bd)
data.append(bd.strip())
datalist.append(data)
# print(datalist)
return datalist
#得到指定一个URL的网页内容
def askURL(url):
head = { #模拟浏览器头部信息,向豆瓣服务器发送消息
"User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122 Safari / 537.36"
}
#用户代理,表示告诉豆瓣服务器,我们是什么类型的机器、浏览器(本质上是告诉浏览器,我们可以接收什么水平的文件内容)
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
#保存数据
if __name__ == "__main__": #当程序执行时
#调用函数
main()
#init_db("movietest.db")
print("爬取完毕!")