python3 def download_python3--有cookie下载网页上的文件

en....

总的来说，就是把这个网页上的我想要的文件先从html里过滤出来，再下载。

其中访问需要cookie，不能通过get直接访问；

脚本如下

#!/usr/bin/python3

import sys, io, re, os

from urllib import request

def get_download_url(sub_url):

url_key_pattern = re.compile(r"href=\".*\"")

url_key = url_key_pattern.findall(str(sub_url))

url_key_pattern = re.compile(r"\/redmine.*\"")

url_key = url_key_pattern.findall(str(url_key))

sub_url = str(url_key[0])

sub_url = sub_url.split('"')

sub_url = str(sub_url[0])

download_url = "http://redmine.springgroup.cn" + sub_url

return download_url

def get_file_name(sub_url):

url_key_pattern = re.compile(r"href=\".*")

url_key = url_key_pattern.findall(str(sub_url))

this_file_name = str(url_key[0])

this_key_pattern = re.compile(r"\>.*?\

this_file_name = this_key_pattern.findall(str(this_file_name))

this_file_name = str(this_file_name[0])

this_file_name = this_file_name.strip('>,

return this_file_name

def pre_fun(save_dir, redmine_number):

#浏览器登录后得到的cookie，也就是刚才复制的字符串

#cookie_str = r'JSESSIONID=xxxxxxxxxxxxxxxxxxxxxx; iPlanetDirectoryPro=xxxxxxxxxxxxxxxxxx'

cookie_str = r'_redmine_session=ajhuOC9xbG9NaWlyUjJ4RTBzcDF4cjl1SVVzUlF4V1dURitCQ2x1U0FpQ1kva1ZrM1ppZ3FDTjVXbnNkdlNHSld3WCt4UjVIYlFBcFhMd29mTVdTc290ZGk5WGRERzl0RmR6V3VubFMxQkF1VGQvQlVGcHdEZWhkMTJFMzNGbVdQSlhYcnJldG8'

os.chdir(save_dir)

if not os.path.isdir(redmine_number):

os.makedirs(redmine_number)

os.chdir(redmine_number)

#登录后才能访问的网页

redmine_url = 'http://redmine.springgroup.cn/redmine/issues/' + redmine_number

return redmine_url, cookie_str

def start_download(redmine_url, cookie_str):

sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='utf8') #改变标准输出的默认编码

req = request.Request(redmine_url)

#设置cookie

req.add_header('cookie', cookie_str)

#设置请求头

req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36')

resp = request.urlopen(req)

#print(resp.read().decode('utf-8'))

#this_text = resp.read().decode('utf-8')

while resp:

li = resp.readline().decode('utf-8')

if "