python 的一个爬虫例子

#-*- codeing = utf-8 -*-
import io
import sys

import urllib.request
import urllib.error
import urllib.parse
from bs4 import BeautifulSoup
import re
import sqlite3
import xlwt

#改变标准输出的默认编码
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='utf8')


def main():
    baseurl = 'https://movie.douban.com/top250?start='

    datalist = getData(baseurl)
    savepath = ".\\豆瓣电影top250.xls"
    
    saveData(datalist,savepath)

findLink = re.compile(r'<a href="(.*?)">') # 生成创建正则表达式对象，表示规则
findTitle = re.compile(r'<span class="title">(.*)</span>') # 生成创建正则表达式对象，表示规则
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')   # 生成创建正则表达式对象，表示规则
findJudge = re.compile(r'<span>(\d*)人评价</span>')  # 生成创建正则表达式对象，表示规则
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)   # 生成创建正则表达式对象，表示规则

# 爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,10):
        url = baseurl + str(i*25)
        html = askURL(url)

        # 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组成列表
            # print(item)
            data = []
            item = str(item)

            link = re.findall(findLink,item)[0]     # 通过正则表达式查找指定的字符串
            title = re.findall(findTitle,item)[0]
            rating = re.findall(findRating,item)[0]
            judge = re.findall(findJudge,item)[0]
            bd = re.findall(findBd,item)[0]
            bd = re.sub("<br(\s+)?/>(\s+)?"," ",bd)     # 去掉<br/>
            bd = re.sub("/"," ",bd)

            data.append(link)
            data.append(title)
            data.append(rating)
            data.append(judge)
            data.append(bd.strip())     # 去掉空格

            datalist.append(data)
    # print(datalist)
    return datalist


def askURL(url):
    # 用户代理，模拟浏览器头部信息
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36'}
    req = urllib.request.Request(url,headers=headers)
    html = ""
    try:
        response = urllib.request.urlopen(req)
        html = response.read().decode('utf-8')
        # print(html)
    except urllib.error.URLError as e:
        print(response.status)
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html 


# 保存数据
def saveData(datalist,savepath):
    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","影片名称","评分","评分人数","详情")
    for i in range(0,5):
        sheet.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):
            sheet.write(i+1,j,data[j])
    book.save(savepath)

if __name__ == "__main__":
    main()