没有任何参考价值,仅供个人记录
最最简单的python爬虫,爬取豆瓣的网页并将电影的网页链接和电影名字保存在excel中
import requests
from pyquery import PyQuery as pq
from openpyxl import load_workbook
def insert_excel(excel,title,rating,link,rows):
sheet = excel.active
sheet.cell(row=rows,column=1).value = title
sheet.cell(row=rows, column=2).value = rating
sheet.cell(row=rows, column=3).value = link
def getDoubanMovie():
excel = load_workbook('test.xlsx')
rows = 1
for page in range(0,250,25):
urls = 'https://movie.douban.com/top250?start=%d&filter='%(page)
content = requests.get(urls).content
for movie in pq(content).find('.item'):
title = pq(movie).find('.title').html()
rating = pq(movie).find('.rating_num').text()
link = pq(movie).find('a').attr('href')
print(title,rating,link,sep='\t\t')
insert_excel(excel,title,rating,link,rows)
rows = rows + 1
excel.save('test.xlsx')
if __name__ == '__main__':
getDoubanMovie()