python 下载文件

下载文件

# coding: UTF-8
#20190106
#源文件 写入   批量下载加个for循环
##单线程下载
import requests
#源地址
str1="sogoupinyinzd423.rar"
url=r"http://down.sd173.com/soft1/"+str1

#目的地  下载的名字叫做 str1
path=str1
r=requests.get(url)
print ("下载完成")
with open(path,"wb") as f:
    f.write(r.content)
f.close()

下载小说

#http://www.coblogs.com/Eva-J/articles/7228075.html#_label10


import requests

import re
import json


def getPage(url):
   response = requests.get(url)
   return response.text


def parsePage(s):
   # com = re.compile(
   #    '<font color="#000">(?P<id>.*?)</font>.*?<td>(?P<kk>.*?)</td>', re.S)
   # print(com)
   # com = re.compile(
   #     '<font color="#000">(?P<id>.*?)</font>.*?<td>(?P<kk>.*?)</td>', re.S)   pk

   com = re.compile(
       '<font color="#000">(?P<id>.*?)</font>.*?<tr><td>(?P<kk>.*?)</td></tr>', re.S)
   # com = re.compile(
   #    '<font color="#000">(?P<id>.*?)</font>.*?<tbody>(?P<kk>.*?)</tbody>', re.S)
   # com = re.compile(
   #       '<a href="/">(?P<id>.*?)</a>', re.S)
   ret = com.finditer(s)
   for i in ret:
       yield {
           "内容": i.group("kk"),
           "题目": i.group("id"),



       }


def main():
       i=[595]
       for j in i:
           print(j)
           url = "/538"+(str)(j)+".html"
           # r = requests.get(url)
           # r.encoding = 'utf8'
           # print (r.text)

           response_html = requests.get(url)
           response_html.encoding = 'utf8'
           # print(response_html.text)
           ret = parsePage(response_html.text)
           f = open("7.txt", "a", encoding="utf8")
           for obj in ret:
               print("ok"+(str)(j))
               data = json.dumps(obj, ensure_ascii=False)
               data = data.replace('<br />', '')
               data = data.replace('\r\n', '')
               f.write(data + "
")
if __name__ == '__main__':
       main()