爬虫爬取猫眼电影top100排名并保存本地Excel或txt

import requests,re
from openpyxl.workbook import Workbook
from openpyxl.writer.excel import ExcelWriter


def get_page(url):
    headers = {
    "User-Agent":"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; de-de) AppleWebKit/534.15+ (KHTML, like Gecko) Version/5.0.3 Safari/533.19.4"
    }
    res = requests.get(url,headers=headers)
    return res.text


def parse_page(html):
    pattern = re.compile(
        "
.*?board-index.*?>(.*?).*?name.*?>(.*?).*?star.*?>\\n(.*?)
.*?releasetime.*?>(.*?)
.*?integer.*?>(.*?)(.*?)
",
        re.S
        )
    items = re.findall(pattern,html)
    # for item in items:
    #     print(item)
    return items


def parse_all():
    top_100 = []
    for i in range(10):
        url = "https://maoyan.com/board/4?offset={0}".format(i*10)
        html = get_page(url)
        item_list = parse_page(html)
        top_100.extend(item_list)
    return top_100
    print(top_100)


def save_list():
    top_100 = parse_all()
    wb = Workbook()
    ws = wb.worksheets[0]

    ws.title = "sheet1"
    ws.cell(row=1, column=1).value = "排名"
    ws.cell(row=1, column=2).value = "电影名"
    ws.cell(row=1, column=3).value = "主演"
    ws.cell(row=1, column=4).value = "上映时间"
    ws.cell(row=1, column=5).value = "评分"

    for i in range(1,len(top_100)+1):
        data_list = top_100[i-1]
        for j in range(1,len(data_list)):
            val = data_list[j-1]
            if j == 3:#正则表达取主演信息式格式有问题，这里调整一下
                val = data_list[j - 1].strip(' ')
            elif j == 5:#评分整数和分数是分开的，这里合到一起
                val = data_list[j - 1] + data_list[j]

            ws.cell(row=i+1, column=j).value = val
    wb.save("猫眼top100电影列表.xlsx")


def main():
    save_list()


if __name__ == "__main__":
    main()

import requests,re
#结果保存为txt格式


def get_page(url):
    headers = {
    "User-Agent":"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; de-de) AppleWebKit/534.15+ (KHTML, like Gecko) Version/5.0.3 Safari/533.19.4"
    }
    res = requests.get(url,headers=headers)
    return res.text


def parse_page(html):
    pattern = re.compile(
        "
.*?board-index.*?>(.*?).*?name.*?>(.*?).*?star.*?>\\n(.*?)
.*?releasetime.*?>(.*?)
.*?integer.*?>(.*?)(.*?)
",
        re.S
        )
    items = re.findall(pattern,html)
    # for item in items:
    #     print(item)
    return items


def parse_all():
    top_100 = []
    for i in range(10):
        url = "https://maoyan.com/board/4?offset={0}".format(i*10)
        html = get_page(url)
        item_list = parse_page(html)
        top_100.extend(item_list)
    return top_100


def save_list():
    top_100 = parse_all()

    for i in range(0,len(top_100)):
        data_list = top_100[i]
        file = open("猫眼电影Top100排行榜.txt","a",encoding="utf-8")
        file.write("\n".join([data_list[0],data_list[1],data_list[2].strip(),data_list[3],data_list[4] + data_list[5]]))
        file.write("\n" + "=" * 50 + "\n")
        file.close()


def main():
    save_list()


if __name__ == "__main__":
    main()