python爬虫爬取爱奇艺电影数据并存入excel

    代码中用了bs4和requests这两个包，这里主要提供下代码，视频教程我建议去https://www.bilibili.com/video/av14109284/?p=1观看，个人觉得课程很棒！

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')

　　这里存在一个小问题就是写数据到excel中这里的代码只能写一页数据进去，后面会报错因为sheet.write()这个函数前两个参数代表excel中的行和列，这部分数据处理放在函数中会导致每次执行这个函数时sheet.write()中的行和列都是从0开始，所以会报错。爬取信息的代码是没有问题的，爬取不同页需要去观察网址的区别。下面贴上excel文件的结果。