from bs4 import BeautifulSoup  # 网页解析，获取数据
import re  # 正则表达，实现文字匹配
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():
    # 1.爬取网页
    baseurl = "https://movie.douban.com/top250?start="
    datalist = getData(baseurl)
    savepath = "豆瓣电影Top250.xlsx"
    # 3.保存数据
    saveData(datalist, savepath)
# 影片链接的规则
findLink = re.compile(r'<a href="(.*?)">')  # 创建正则表达式对象，表示规则（字符串表达式）
# 影片的图片的规则
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)  # re.S让换行符包含在字符中
# 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>')
# 找到影片相关内容
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)
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，形成一个链表
            # print(item) #测试
            data = []  # 保存一部电影的所有信息
            item = str(item)
            link = re.findall(findLink, item)[0]  # re库用来通过正则表达式查找指定内容
            data.append(link)
            imgSrc = re.findall(findImgSrc, item)[0]  # 添加图片
            data.append(imgSrc)
            titles = re.findall(findTitle, item)  # 片名可能只有一个中文名
            if (len(titles) == 2):
                ctitle = titles[0]
                data.append(ctitle)  # 添加中文名
                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(' ')  # 外国名留空
            rating = re.findall(findRating, item)[0]  # 添加评分
            data.append(rating)
            judgeNom = re.findall(findJudge, item)[0]  # 添加评价人数
            data.append(judgeNom)
            inq = re.findall(findInq, item)
            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())  # 去掉前后空格
            datalist.append(data)
    return datalist
def saveData(datalist, savepath):
    print("save....")
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建workbook对象
    sheet = book.add_sheet('豆瓣电影Top250', 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", "影片外国名", "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)
        data = datalist[i]
        for j in range(0, 8):
            sheet.write(i + 1, j, data[j])
    book.save(savepath)
def askURL(url):
    head = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:90.0) Gecko/20100101 Firefox/90.0"}
    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    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()
    print("爬取完毕")

import json
import requests
def ku6_spider():
    for page in range(0,11):
        print('正在抓取第{}页数据'.format(page+1))
        #1.确定URL路径，headers参数
        base_url = 'https://www.ku6.com/video/feed'
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
        }
        params = {
            'pageNo': str(page),
            'pageSize': '40',
            'subjectId': '76',
        }
        #2.模拟浏览器-requests发送请求获取数据
        response = requests.get(base_url,headers=headers,params=params)
        res_data = response.text
        #print(res_data)
        #3.解析数据
        json_data = json.loads(res_data)    #--字典
        data_list = json_data['data']
        #遍历列表
        for data in data_list:
            #print(data)
            video_name = data['title']+".mp4"
            video_url = data['playUrl']
            #print(video_url,video_name)
            print('下载中：',video_name)
            video_data = requests.get(video_url,headers=headers).content
            #4.保存数据
            with open('video\\'+video_name,'wb') as f:
                f.write(video_data)
                print('下载完成...')
if __name__ == '__main__':
    ku6_spider()