猫眼100 爬虫

正则表达式爬虫

完整代码

import requests  # 获取网页数据
import re  # 正则表达式
from bs4 import BeautifulSoup  # 网页解析，获取数据
import xlwt  # 保存为excel

findIndex = re.compile(r'board-index.*?>(\d+).*?')
findImage = re.compile(r'class="board-img".*?src="(.*?)"')
findTitle = re.compile(r'title="(.*?)">')
findActor = re.compile(r'class="star">(.|\n)(.*)')
findTime = re.compile(r'class="releasetime">(.*?)</p> ')
findScore1 = re.compile(r'class="integer">(.*?)</i>')
findScore2 = re.compile(r'class="fraction">(.*?)</i>')


# 爬取网页
# 解析数据
# 保存数据

def main():
    baseurl = "https://maoyan.com/board/4?offset="
    datalist = getData(baseurl)
    savepath = "猫眼TOP100.xls"
    saveData(datalist, savepath)


def getData(baseUrl):
    datalist = []
    for i in range(0, 10):
        url = baseUrl + str(i * 10)
        html = askUrl(url)
        # 解析数据
        soup = BeautifulSoup(html, "html.parser")

        for item in soup.find_all("dd"):
            # print(item)  # 测试
            data = []
            item = str(item)
            # 排名
            index = re.findall(findIndex, item)[0]
            data.append(index)
            # 图片地址
            image = re.findall(findImage, item)[0]
            data.append(image)
            # 标题
            title = re.findall(findTitle, item)[0]
            data.append(title)
            # 作者
            actor = re.findall(findActor, item)[0]
            actorList = list(actor)
            for i in actorList:
                actorNew = "".join(i).strip()
            data.append(actorNew)
            # 上映时间
            time = re.findall(findTime, item)[0]
            data.append(time)
            # 成绩
            score1 = re.findall(findScore1, item)[0]
            # data.append(score1)
            score2 = re.findall(findScore2, item)[0]
            # data.append(score2)
            score = score1 + score2
            data.append(score)

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


# 爬取网页
def askUrl(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4209.2 Safari/537.36"}

    html = ""
    try:
        response = requests.get(url, headers=headers)
        html = response.content.decode("utf-8")
        # print(html)
    except requests.exceptions 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")
    sheet = book.add_sheet("猫眼TOP100", cell_overwrite_ok=True)
    col = ("电影排名", "图片地址", "电影名称", "演出人员", "上映时间", "电影评分")
    for i in range(0, 6):
        sheet.write(0, i, col[i])
    for i in range(0, 100):
        print("第%d条" % (i + 1))
        try:
            data = datalist[i]
        except:
            continue
        for j in range(0, 6):
            sheet.write(i + 1, j, data[j])
    book.save(savepath)


if __name__ == '__main__':  # 当程序执行时调用函数
    main()
    print('爬取完成')