python爬蟲爬取愛奇藝電影數據並存入excel

    代碼中用了bs4和requests這兩個包，這里主要提供下代碼，視頻教程我建議去https://www.bilibili.com/video/av14109284/?p=1觀看，個人覺得課程很棒！

from bs4 import BeautifulSoup
import requests
import time
import xlwt

urls = ['http://list.iqiyi.com/www/1/4-------------11-{}-1-iqiyi--.html'.format(str(i)) for i in range(1,2)]
def get_webData(url):
    data_info = []
    time.sleep(3)
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text,'lxml')
    titles = soup.select('div.site-piclist_info > div.mod-listTitle_left > p > a')
    imgs = soup.select('div.site-piclist_pic > a > img')
    actors = soup.select('div.site-piclist_info > div.role_info')
    spans = soup.select('div.site-piclist_info > div.mod-listTitle_left > span')
    for title,img,actors,span in zip(titles,imgs,actors,spans):
        data = {
                'title':title.get_text(),
                'img':img.get('src'),
                'actors':list(actors.stripped_strings),
                'span':span.get_text()
                }
        #print(data) 
        dataVal_list.append(data.values())
        data_info.append(data)
    #print(list(data.keys())) 
    for m,n in enumerate(list(data.keys())):
        sheet.write(0,m,n)
            
    for i,p in enumerate(dataVal_list):
        for j,q in enumerate(p):
            #print(q)
            sheet.write(i+1,j,q)
    return data_info
def main():
    for url in urls:
        data_info = get_webData(url)
        #print(data_info)
        print('---------------------------\n')

if __name__ == '__main__':
    f = xlwt.Workbook(encoding='utf-8')
    sheet = f.add_sheet('Movies')
    dataVal_list=[]
    main()
    f.save('Movies.xls')

　　這里存在一個小問題就是寫數據到excel中這里的代碼只能寫一頁數據進去，后面會報錯因為sheet.write()這個函數前兩個參數代表excel中的行和列，這部分數據處理放在函數中會導致每次執行這個函數時sheet.write()中的行和列都是從0開始，所以會報錯。爬取信息的代碼是沒有問題的，爬取不同頁需要去觀察網址的區別。下面貼上excel文件的結果。