一个爬虫Demo（经典豆瓣TOP250）

TRXCX

于 2024-03-10 19:10:22 发布

阅读量1.1k

点赞数 1

分类专栏： Python 文章标签：爬虫

本文链接：https://blog.youkuaiyun.com/TRXCXS/article/details/136606808

版权

获取网页源码，拿想要的内容就完事了。

import xlwt
import requests
from bs4 import BeautifulSoup


def get_style():
    style = xlwt.XFStyle()

    alignment = xlwt.Alignment()
    alignment.horz = 0x02
    alignment.vert = 0x01
    style.alignment = alignment

    font = xlwt.Font()
    font.name = '仿宋'
    style.font = font

    return style


def get_excel(style):
    workbook = xlwt.Workbook(encoding='ascii')
    worksheet = workbook.add_sheet("MovieTop250")

    col_names = ["排名", "影名", "评论", "链接"]
    for i in range(len(col_names)):
        worksheet.write(0, i, col_names[i], style)

    worksheet.col(0).width = 100 * 20
    worksheet.col(1).width = 400 * 20
    worksheet.col(2).width = 1200 * 20
    worksheet.col(3).width = 650 * 20

    return workbook, worksheet


def crawler(worksheet, style):
    headers = {