[爬虫]爬取百度热搜(excel)

要求

爬取的数据写入excel表格

代码

#单   位:常州旺龙
#作   者:OLDNI
#开发日期:2023/11/16
'''
爬取进度热搜：https://top.baidu.com/board?tab=realtime
生成excel表格
'''
import os

from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill, Alignment
from selenium import webdriver
from selenium.webdriver.common.by import By

options=webdriver.ChromeOptions()
#解决闪退
options.add_experimental_option('detach',True)
#无头模式
options.add_argument('--headless')
#让浏览器更难检测到自动化软件的存在
options.add_argument('--disable-blink-features=AutomationControlled')
# 隐藏"正在受到自动软件的控制"这几个字
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)

#创建浏览器对象
browser=webdriver.Chrome(options=options)
#打开指定网址
browser.get('https://top.baidu.com/board?tab=realtime')

#创建excel表格
wb=Workbook()
sheet=wb.active
header=['排名','标题','简介',]
sheet.append(header)


#获取循环标签的列表
div_tag_list=browser.find_elements(By.CSS_SELECTOR,'.category-wrap_iQLoo.horizontal_1eKyQ')

#排名
ranking1=range(1,51)
r_l=['置顶']
for r in ranking1:
    r_l.append(r)

#从每个标签内获取数据
n=0   #用于排名列表下标
for div_tag in div_tag_list:
    ranking=r_l[n]
    title=div_tag.find_element(By.CSS_SELECTOR,'.content_1YWBm .c-single-text-ellipsis').text
    profile=div_tag.find_element(By.CSS_SELECTOR,'.content_1YWBm >div:nth-child(2)').text.split('查看更多>')[0].strip()
    data=[ranking,title,profile]
    sheet.append(data)
    n+=1
browser.close()

#设置列宽
column_number_and_dimensions={'A':6,'B':36,'C':128,}
for n,d in column_number_and_dimensions.items():
    sheet.column_dimensions[n].width = d
#设置表头样式
cells=sheet[1]
font=Font(bold=True)
patternfill=PatternFill(fill_type='solid',fgColor='FFFF00')
alignment=Alignment(horizontal='center')
for cell in cells:
    cell.font=font
    cell.fill=patternfill
    cell.alignment=alignment
#冻结窗格
sheet.freeze_panes='A2'

wb.save('百度热搜.xlsx')
os.startfile('百度热搜.xlsx')

效果