python数据保存为txt_python爬取数据保存为txt格式

#encoding:'utf-8'

import urllib.request

from bs4 import BeautifulSoup

import os

import time

#找到网址

def getDatas():

url="https://movie.douban.com/top250"

# url="file:///E:/scrapy/2018-04-27/movie/movie.html"

# 打开网页

res=urllib.request.urlopen(url)

# 转化格式

response=BeautifulSoup(res,'html.parser')

# 找到想要数据的父元素

datas=response.find_all('div',{'class':'item'})

# print(datas)

#创建存放数据的文件夹

folder_name="output"

if not os.path.exists(folder_name):

os.mkdir(folder_name)

# 定义文件

current_time=time.strftime('%Y-%m-%d',time.localtime())

file_name="move"+current_time+".txt"

# 文件路径

file_path=folder_name+"/"+file_name

for item in datas:

# print(item)

rank=item.find('div',{'class':'pic'}).find('em').get_text()

title=item.find('div',{'class':'info'}).find('div',{'class':'hd'}).find('a').find('span',{'class':'title'}).get_text()

picUrl=item.find('div',{'class':'pic'}).find('a').find('img').get('src')

# print(picUrl)

# 保存数据为txt格式

try:

with open(file_path,'a',encoding="utf-8") as fp:

fp.write("排名:"+rank+'\n')

fp.write("标题:"+title+'\n')

fp.write("图片路径:"+picUrl+'\n\n')

except IOError as err:

print('error'+str(err))

finally:

fp.close()

pass

getDatas()

# 爬取数据

阅读更多