Python自动化驱动实战

星_奕

已于 2023-04-24 19:51:22 修改

阅读量185

点赞数

文章标签： python 开发语言

于 2023-04-24 19:49:19 首次发布

本文链接：https://blog.csdn.net/xuan_kong/article/details/130350497

版权

该代码使用Python的Selenium库无头模式浏览猫眼电影排行榜网页，抓取电影的排名、名称、主演、上映时间和评分等信息，并将数据保存到Excel表格中。程序还包括自动点击下一页进行多页抓取及异常处理。

摘要由CSDN通过智能技术生成

# -*- coding: utf-8 -*-
# 猫眼数据
import random
import time
from openpyxl import workbook

from selenium import webdriver
from selenium.webdriver.common.by import By

url = "https://www.maoyan.com/board/4?offset=0"

# driver.find_element(By.ID, 'kw').send_keys('小奕')
# driver.find_element(By.CLASS_NAME, "bg.s_btn").click()
options = webdriver.ChromeOptions()
options.add_argument('--headless')
driver = webdriver.Chrome(options=options)
driver.get(url)
# driver.maximize_window()

workbook = workbook.Workbook()
sheet = workbook.worksheets[0]
table_title = ["排名", "电影名称", "主演", "上映时间", "评分"]
for i, item in enumerate(table_title, 1):
    cell = sheet.cell(1, i)
    cell.value = item


def get_data():
    dds = driver.find_elements(By.XPATH, '//*[@id="app"]/div/div/div[1]/dl/dd')
    # print(dds)
    # print(type(dds))
    for j in dds:
        data = j.text.split("\n")
        print(data)
        li = [
            data[0].strip(),
            data[1].strip(),
            data[2].strip(),
            data[3].strip(),
            data[4].strip()
        ]
        print(li)
        # print(type(li))
        max_row = sheet.max_row
        for h, items in enumerate(li, 1):
            cells = sheet.cell(max_row + 1, h)
            cells.value = items
        workbook.save("maoyan.xlsx")


while True:
    get_data()
    try:
        time.sleep(random.randint(2, 3))
        driver.find_element(By.LINK_TEXT, "下一页").click()
    except Exception as e:
        print(e)
        print("爬取完成")
        driver.quit()
        break