# coding=utf-8
# 第一行要加它，不然会报错

# https://movie.douban.com/top250?start=28&filter=
# 豆瓣top250网址，重点在于start=?,代表从哪个序号往后开始，filter不重要，可以去掉
# chrome浏览器f12 点进network 点击流线图的颜色线，然后点击下面Name对应的访问信息，就可以查看header
# 在Headers中，是用户向浏览器发送信息，重点在于user-Agent和Cookies

# python文件中可以加入main函数用于测试程序
# if __name__=="__main__":  当程序执行时调用函数

# 引入自定义模块，就是引入别人写好的函数： from 包名 import 函数
# 引入系统模块：import sys, import os
# 引入第三方模块 import re
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


# 主函数
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top250.xls"
    saveData(datalist, savepath)
    # askUrl("https://movie.douban.com/top250?start=0")


# 影片详情链接规则
findLink = re.compile(r'<a href="(.*?)">')
findImgSrc = re.compile(r'<img .* src="(.*?)"', re.S)  # re.S让换行符包含在字符中
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)


# 获取数据函数
def getData(baseurl):
    datalist = []
    for i in range(0, 10):  # for循环，左闭右开
        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"):
            # print(item)
            data = []  # 保存一部电影所有信息
            item = str(item)
            # 获取到影片详情链接
            link = re.findall(findLink, item)
            # print(link)
            data.append(link)
            # 找到图片
            imgSrc = re.findall(findImgSrc, item)
            data.append(imgSrc)
            # print(imgSrc)
            # 因为有的名字没有英文名，所以要进行判断
            titles = re.findall(findTitle, item)
            # print(titles)
            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)
            data.append(rating)

            judgeNum = re.findall(findJudge, item)
            # print(judgeNum)
            data.append(judgeNum)

            inq = re.findall(findInq, item)
            if len(inq) != 0:
                inq = inq[0].replace("。", "")
                data.append(inq)
            else:
                data.append(" ")

            data.append(inq)

            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)
    # print(datalist)
    return datalist


# 得到指定一个Url的网页内容
def askUrl(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36"
    }
    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


# 保存数据函数
def saveData(datalist, savepath):
    print("正在保存中")
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建workbook对象
    sheet = book.add_sheet('sheet1', cell_overwrite_ok=True)  # 创建工作表
    col = ("电影详情链接", "图片链接", "影片中文名", "影片英文名", "评分", "评价数", "概况", "相关信息")
    for i in range(0, 8):
        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, 8):
            sheet.write(i + 1, j, data[j])

    book.save(savepath)  # 保存


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