python爬取豆瓣电影TOP250信息

# -*- coding:utf-8 -*-
import urllib.request
import jsonpath
import json
import re # 正则表达式
import xlwt # 进行excel操作
import sqlite3 # 进行SQLite数据库操作
from bs4 import BeautifulSoup # 网页解析，获取数据


# 需要的访问内容,创建增则表达式对象
findLink = re.compile(r'<a href="(.*?)">')  # 网页链接
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)  # 图片,re.S是让换行符包含在字符中
findTitle = re.compile(r'<span class="title">(.*?)</span>')  # 片名
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*?)</span>')  # 评分
findJudge = re.compile(r'<span>(\d*)人评价</span>')  # 评分人数
findInq = re.compile(r'<span class="inq">(.*?)</span>')  # 找概况
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)  # 相关内容


# 爬虫爬取豆瓣前250电影信息
def main():
    baseurl = "https://movie.douban.com/top250?start="
    # 1.爬取网页
    datalist = getData(baseurl)
    # 3.保存数据
    savepath = ".\\豆瓣电影Top.xls"
    saveData(datalist,savepath)
    print("爬取完毕")


# 1.爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0, 250, 25):
        url = baseurl + str(i)
        html = askURL(url)
        # 2.解析数据
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all('div', class_="item"):
            data = []  # 保存这个电影所有信息
            item = str(item)
            # re通过正则表达式找链接
            link = re.findall(findLink, item)[0]
            data.append(link)
            # 图片
            imgSrc = re.findall(findImgSrc, item)[0]
            data.append(imgSrc)
            # 片名
            titles = re.findall(findTitle, item)
            if len(titles) >= 2:
                ctitle = titles[0]  # 中文名
                data.append(ctitle)
                otitle = titles[1].replace("/", "")  # 外文名，去掉斜杠
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append("")  # 留空，保证数据对齐
            # 打分
            rating = re.findall(findRating, item)
            data.append(rating)
            # 评价人数
            judgeNum = re.findall(findJudge, item)
            data.append(judgeNum)
            # 概述
            inq = re.findall(findInq,item)
            if len(inq)!=0:
                inq = inq[0].replace("。","")
            else:
                inq = " " # 留空，保证数据对齐
            data.append(inq)
            # 相关内容
            bd = re.findall(findBd,item)[0]
            bd = re.sub('<br(\s+)?/>(\s+)?'," ",bd) # 去掉<br/>
            bd = re.sub('/'," ",bd) # 去掉 / 
            data.append(bd.strip()) # 去掉空格 
            datalist.append(data)
    return datalist


# 3.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","图片","中文名","外文名","评分","评价数","概况","相关信息")
    for i in range(8):
        sheet.write(0,i,col[i])
    for i in range(len(datalist)):
        print("第%d条"%i)
        data = datalist[i]
        for j in range(len(data)):
            sheet.write(i+1,j,data[j])    
    book.save(savepath)


# 访问URL
def askURL(url):
    head = {
        "User-Agent": "Mozilla/5.0(Windows NT 10.0;Win64;x64)AppleWebKit/537.36(KHTML,like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18363"
    }
    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


if __name__ == "__main__":
    main()