#!/usr/bin/python3
# coding: utf-8 
"""
__title__ = "my crawler"
__author__ = "Hans"
__mtime__ = "2017/3/30 0030"
# code is far away from bugs with the god animal protecting
I love animals. They taste delicious.
┏┓ ┏┓
┏┛┻━━━┛┻┓
┃ ☃ ┃
┃ ┳┛ ┗┳ ┃
┃ ┻ ┃
┗━┓ ┏━┛
┃ ┗━━━┓
┃ 神兽保佑 ┣┓
┃　永无BUG！ ┏┛
┗┓┓┏━┳┓┏┛
┃┫┫ ┃┫┫
┗┻┛ ┗┻┛
"""
from bs4 import BeautifulSoup
import socket
import urllib.parse

site = 'www.quanjing.com'
sock = socket.socket()
# sock.setblocking(False)


sock.connect((site, 80))

get = 'GET / HTTP/1.0\r\nHost: {}\r\n\r\n'.format(site)
sock.send(get.encode('utf-8'))
response = b''
while True:
    chunk = sock.recv(4096)
    print(type(chunk))
    if not chunk:
        break
    response += chunk

# 将response内容进行拆分
header, body = response.split(b'\r\n\r\n', 1)
# print(body.decode())

# with open('index.html', 'wb') as f:
#     f.write(response)


soup = BeautifulSoup(body, 'lxml')
# print(soup.prettify())


# print(''.join(soup.find_all('img')))
# print(str(soup.find_all('img')[0]))
imgs = soup.find_all('img')
print(len(imgs))
# with open('image.html', 'w') as f:
#     for img in imgs:
#         print(type(img))
#         f.write(str(img.encoding('utf-8'), encoding="utf-8"))
#         f.write('<br><hr>')
#         f.write('\r\n')
for img in imgs:
    print(urllib.parse.unquote(img['src']))

links = soup.find_all('a')
print('-'*100)
for link in links:
    try:
        print(urllib.parse.unquote(link['href']))
    except:
        pass
    # url =  urllib.parse.unquote(link['href'])
    # p_url = urllib.parse.urlparse(url)
    # print(p_url)


# with open('image.html', 'w') as f:
#     for link in links:
#         try:
#             f.write(str(link))
#             f.write('\r\n')
#         except:
#             pass