python 爬虫 豆瓣

# Author:杨傲天
# -*- codeing = utf-8 -*-
# @Time: 2022/1/22 16:56
# @File: douban.py
# @Software:PyCharm
import re
import urllib.request
import urllib.parse
from bs4 import BeautifulSoup
from testXwlt import saveData
import xlwt
'''
data=bytes(urllib.parse.urlencode({"hello":"YangAoTian","haha":"shuai"}),encoding="utf-8")

try:
    response=urllib.request.urlopen("http://httpbin.org/get",timeout=0.01)
    print(response.read().decode("utf-8"))
except urllib.error.URLError as e:
    print("time out!")
'''
# url = "http://httpbin.org/post"
'''
url = "https://www.douban.com"
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36 Edg/97.0.1072.76"
}
data = bytes(urllib.parse.urlencode({'name':'eric'}),encoding='utf-8')

req = urllib.request.Request(url=url,data=data,headers=headers,method="POST")
response = urllib.request.urlopen(req)
print(response.read().decode("utf-8"))
'''
# 影片详情链接的规则
findLink = re.compile(r'<a href="(.*?)">')  #创建正则表达式对象，表示规则（字符串的模式）
#影片图片的链接
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S) #re.S的作用是扩大.的范围（即任意字符），让换行符也包含在字符中
#影片片名
findTitle = re.compile(r'<span class="title">(.*)</span>')
#影片评分
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
#找到评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
#找到概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
#找到影片的相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)

#爬取网页
def getData(baseurl):
    datalist=[]
    for i in range(0,10):  #左闭右开
        url = baseurl + str(i*25)
        html = askURL(url)   #保存获取到的网页源码
        #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，形成列表
            #print(item)     #测试：查看电影item全部信息
            data = [] #保存一部电影的所有信息
            item = str(item)
            #re库用来通过正则表达式查找指定的字符串，通过findLink找到item中的第一个（[0]）
            link = re.findall(findLink,item)[0]  #添加链接
            data.append(link)
            imgSrc = re.findall(findImgSrc,item)[0]
            data.append(imgSrc)                      #添加图片
            titles = re.findall(findTitle,item)      #片名可能只有一个中文名，没有外国名
            if(len(titles) == 2):
                ctitle = titles[0]                   #添加中文名
                data.append(ctitle)
                otitle = titles[1].replace("/","")   #去掉无关的符号
                data.append(otitle)                  #添加外国名
            else:
                data.append(titles[0])
                data.append(' ')

            rating = re.findall(findRating,item)[0]
            data.append(rating)                      #增加评分

            judgeNum = re.findall(findJudge,item)[0]
            data.append(judgeNum)

            inq = re.findall(findInq,item)             #添加概述
            if len(inq) !=0:
                inq = inq[0].replace("。","")         #去掉句号
                data.append(inq)                     #添加概述
            else:
                data.append(" ")                     #留空

            bd = re.findall(findBd,item)[0]
            bd = re.sub('<br(\s+)?/>(\s+)?'," ",bd)   #去掉<br/>
            bd = re.sub('/'," ",bd)     #替换/
            data.append(bd.strip())     #去掉前后的空格

            datalist.append(data)  #把处理好的一部电影信息放入datalist
    print(datalist[0])
    a=datalist[0]
    print(a[0])
    return datalist

#得到指定一个URL的网页内容
def askURL(url):
    headers={
        
    }
    request = urllib.request.Request(url=url,headers=headers)  #封装
    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 saveDATA(datalist,savepath):
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建workbook对象  样式压缩
    sheet = book.add_sheet('豆瓣电影TOP250', cell_overwrite_ok=True)  # 创建工作表    是否可以覆盖
    col = ("电影详情链接", "图片链接", "影片中文名", "影片外国名", "评分", "评价数", "概况", "相关信息")  # 定义元组
    for i in range(8):
        sheet.write(0, i, col[i])  # 列名
    for i in range(250):
        print("第%d条" % (i + 1))
        data = datalist[i]   #这里提取了第i部电影的元组内全部信息
        for j in range(0, 8):
            sheet.write(i + 1, j, data[j])

    book.save('student.xls')  # 保存数据表

def main():
    baseurl = "https://movie.douban.com/top250?start="
    datalist = getData(baseurl)
    savepath = ".\\豆瓣电影Top250.xls"
    saveData(datalist,savepath)





if __name__ == '__main__':
    main()
    print("爬取完毕！")