|
| 1 | +#!/usr/bin/env python |
| 2 | +# encoding: utf-8 |
| 3 | + |
| 4 | +""" |
| 5 | +@author: zhanghe |
| 6 | +@software: PyCharm |
| 7 | +@file: ganji_callback.py |
| 8 | +@time: 2017/8/18 下午4:18 |
| 9 | +""" |
| 10 | + |
| 11 | + |
| 12 | +import time |
| 13 | +import lxml.html |
| 14 | +import requests |
| 15 | +from urlparse import urljoin |
| 16 | + |
| 17 | +from requests.exceptions import Timeout |
| 18 | + |
| 19 | + |
| 20 | +header = { |
| 21 | + 'Host': 'callback.ganji.com', |
| 22 | + 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36' |
| 23 | +} |
| 24 | + |
| 25 | + |
| 26 | +s = requests.session() |
| 27 | + |
| 28 | + |
| 29 | +callback_url = 'http://callback.ganji.com/firewall/valid/1709685058.do?namespace=ganji_hy_list_pc&url=http%3A%2F%2Fanshan.ganji.com%2Fbanjia%2F' |
| 30 | + |
| 31 | + |
| 32 | +def fuck(): |
| 33 | + r_g = s.get(callback_url) |
| 34 | + html = r_g.text |
| 35 | + doc = lxml.html.fromstring(html) |
| 36 | + |
| 37 | + # 获取页面隐藏域表单 |
| 38 | + uuid = doc.xpath('//input[@id="uuid"]/@value')[0].strip() |
| 39 | + url = doc.xpath('//input[@id="url"]/@value')[0].strip() |
| 40 | + namespace = doc.xpath('//input[@id="namespace"]/@value')[0].strip() |
| 41 | + ip = doc.xpath('//input[@id="ip"]/@value')[0].strip() |
| 42 | + |
| 43 | + # 获取验证码图片 |
| 44 | + img_url_text = doc.xpath('//img[@id="verify_img"]/@src')[0].strip() |
| 45 | + img_url = urljoin(callback_url, img_url_text) |
| 46 | + print img_url |
| 47 | + |
| 48 | + # 保存验证码图片 |
| 49 | + img_name = 'ganji_%s.jpg' % uuid |
| 50 | + img_content = s.get(img_url).content |
| 51 | + with open(img_name, 'w') as f: |
| 52 | + f.write(img_content) |
| 53 | + time.sleep(5) |
| 54 | + |
| 55 | + verify_code = raw_input('verify_code') |
| 56 | + |
| 57 | + print uuid |
| 58 | + print url |
| 59 | + print namespace |
| 60 | + print ip |
| 61 | + print r_g.cookies.__dict__ |
| 62 | + data = { |
| 63 | + 'namespace': namespace, |
| 64 | + 'uuid': uuid, |
| 65 | + 'url': url, |
| 66 | + 'verify_code': verify_code |
| 67 | + } |
| 68 | + r_p = s.post(callback_url, data=data) |
| 69 | + r_p_json = r_p.json() # {"msg":"验证码过期.","code":-1} |
| 70 | + print r_p_json |
| 71 | + if r_p_json.get('code') == 0: |
| 72 | + print u'识别成功' |
| 73 | + else: |
| 74 | + print r_p_json.get('msg') |
| 75 | + |
| 76 | + |
| 77 | +if __name__ == '__main__': |
| 78 | + fuck() |
| 79 | + |
| 80 | + |
| 81 | +""" |
| 82 | +# 获取页面隐藏域表单 |
| 83 | +<input type="hidden" id="uuid" value="25f77df09ff249a0942c78e46c79dc89" /> |
| 84 | +<input type="hidden" id="url" value="http://anshan.ganji.com/banjia/" /> |
| 85 | +<input type="hidden" id="namespace" value="ganji_hy_list_pc" /> |
| 86 | +<input type="hidden" id="ip" value="1709685058" /> |
| 87 | +
|
| 88 | +# 查看出口IP |
| 89 | +➜ ~ curl ifconfig.me |
| 90 | +101.231.185.66 |
| 91 | +
|
| 92 | +# 验证IP |
| 93 | +In [1]: 101*256*256*256 + 231*256*256 + 185*256 + 66 |
| 94 | +Out[1]: 1709685058 |
| 95 | +
|
| 96 | +买一送一,童叟无欺 |
| 97 | +58也是一样的: |
| 98 | +http://callback.58.com/firewall/valid/920593415.do?namespace=huangyedetailpc&url=http%3A%2F%2Finfodetail1.58.com%2Fsz%2Fjisuanji%2F27978971970226x.shtml |
| 99 | +""" |
0 commit comments