马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
Python 爬取豆瓣TOP250 电影整理到EXCELimport re
import requests
import xlsxwriter
from bs4 import BeautifulSoup
str1 = '\S+'
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/83.0.4103.14 Safari/537.36 Edg/83.0.478.13"}
rank = []
for i in range(1, 251):
rank.append('第' + str(i))
workbook = xlsxwriter.Workbook('豆瓣电影top250.xlsx')
worksheet = workbook.add_worksheet('sheet1')
heading = ['排名', '电影名'] # 设置表头
worksheet.write_row('A1', heading)
list1 = []
for i in range(0, 250, 25):
html = requests.get('https://movie.douban.com/top250?start=' + str(i) + '&filter=', headers=headers).text
soup = BeautifulSoup(html, "html.parser")
ol = soup.find('ol', class_='grid_view')
a = ol.find_all('a')
for each in a:
name = re.findall(str1, each.text)
if len(name) != 0:
print(name)
list1.append(name[0])
worksheet.write_column('B2', list1) # 为excel表的B列从B2开始写入数据
worksheet.write_column('A2', rank)
workbook.close()
|