Python 百度热搜 全页面爬取

import requests
import xlwt
from bs4 import BeautifulSoup


def getCid():
    hd = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.4071 SLBChan/21"}
    url = "https://top.baidu.com/board"
    page = requests.get(url,headers=hd).content.decode("utf-8")
    soup = BeautifulSoup(page, 'html.parser')
    dIv = soup.find_all('a', attrs={'class':"tab-item_17MbK"})

    code = []

    type_L = []

    for i in dIv:
        src = i['href']
        code.append(src.strip('.'))
        type_L.append(i.text)

    return code,type_L

def getItem(page):

    hd = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.4071 SLBChan/21"}
    url = "https://top.baidu.com%s"
    url = url%page
    page = requests.get(url,headers=hd).content.decode("utf-8")
    soup = BeautifulSoup(page, 'html.parser')

    code = []
    tBody = soup.find('div',attrs={'style':"margin-bottom:20px"})
    name_M = tBody.find_all('a',attrs={'class':"title_dIF3B"})
    text_M = tBody.select("div[class^='hot-desc_1m_jR large_nSuFU']")
    top_M = tBody.find_all('a', attrs={'class': "img-wrapper_29V76"})
    score_M = tBody.find_all('div', attrs={'class': "hot-index_1Bl1a"})
    for i in range(0,len(name_M)):
        # code.append(dict(排名=top_M[i].div.text,标题=name_M[i].text,分数=score_M[i].text))
        code.append([top_M[i].div.text,name_M[i].text,score_M[i].text])
    return code

def saveExcel(result,type_L):
    wb = xlwt.Workbook()  # 创建工作表
    for i in range(0,len(type_L)):
        sheet = wb.add_sheet(type_L[i])
        list_h = ['排名','标题','分数']
        for row,str in enumerate(list_h):
            sheet.write(0, row, str)
        for m in range(0,len(result[i])):
            for n,inV in enumerate(list_h):
                sheet.write(m+1,n,result[i][m][inV])
    wb.save('热搜全爬.xlsx')

from openpyxl import Workbook
def OaveExcel(data):
    workbook = Workbook()
    sheet = workbook.create_sheet()
    for x in data:
        sheet.append(x)
    workbook.save('热搜全爬.xlsx')



page,type_L=getCid()
all_S = []
del page[0]
del type_L[0]
for i in range(0,len(page)):
    all_S.append(getItem(page[i]))

saveExcel(all_S,type_L)