txt保存

全代码：

import requests
from bs4 import BeautifulSoup
import os
import time
import sys
import io
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')
#找到网址
def getDatas():
    header={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'}
    url="https://movie.douban.com/top250"
    # url="file:///E:/scrapy/2018-04-27/movie/movie.html"
    # 打开网页
    res=requests.get(url,headers=header)
    # 转化格式
    response=BeautifulSoup(res.text,'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()

当然了 爬取过程中不免有各种各样的问题出现 我出现 408 错误；网上找到408  错误说是触发了反爬取；

解决办法：

 header={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'}
    url="https://movie.douban.com/top250"
    # url="file:///E:/scrapy/2018-04-27/movie/movie.html"
    # 打开网页
    res=requests.get(url,headers=header)

就ok了

然后是结果：