|
|
@@ -0,0 +1,90 @@
|
|
|
+# -*- coding: utf-8 -*-
|
|
|
+"""
|
|
|
+Created on 2023-08-08
|
|
|
+---------
|
|
|
+@summary: jsl+创宇云盾 通用模板
|
|
|
+---------
|
|
|
+@author: jsl、创宇5秒盾
|
|
|
+"""
|
|
|
+import re
|
|
|
+import sys
|
|
|
+import json
|
|
|
+import execjs
|
|
|
+import requests
|
|
|
+sys.path.append('/app/spiders/sword_feapder/FworkSpider')
|
|
|
+from untils.cookie_pool import PageCookiePool
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+class DTCookiePool(PageCookiePool):
|
|
|
+ def __init__(self,redis_key,header,page_url=None,**kwargs):
|
|
|
+ super(DTCookiePool, self).__init__(redis_key,page_url=None,
|
|
|
+ min_cookies=10000,must_contained_keys=(),keep_alive=False,**kwargs)
|
|
|
+ self.headers=header
|
|
|
+ self.page_url = page_url
|
|
|
+ self.proxies = kwargs.get('proxies') or False
|
|
|
+
|
|
|
+ def create_cookie(self):
|
|
|
+
|
|
|
+ proxies = self.proxies
|
|
|
+
|
|
|
+ session = requests.Session()
|
|
|
+ session.proxies = proxies
|
|
|
+ start_url = self.page_url
|
|
|
+ res = session.get(start_url, headers=self.headers,timeout=120, verify=False)
|
|
|
+ js_func = "".join(re.findall("document.cookie=(.*?)location.href", res.text))
|
|
|
+ js_func = 'function sd() { return ' + js_func + "}"
|
|
|
+ ctx = execjs.compile(js_func)
|
|
|
+ sss = ctx.call("sd")
|
|
|
+ cookie = {}
|
|
|
+ for temp, index in res.cookies.get_dict().items():
|
|
|
+ cookie[temp] = index
|
|
|
+
|
|
|
+ for item in sss.split(";"):
|
|
|
+ if '=' in item:
|
|
|
+ cookie[item.split("=")[0]] = item.split("=")[-1]
|
|
|
+
|
|
|
+ res = session.get(start_url, cookies=cookie,headers=self.headers,timeout=120,verify=False)
|
|
|
+ html_str = res.content.decode()
|
|
|
+ if "<!DOCTYPE html>" in html_str:
|
|
|
+ html_str = re.sub("<!DOCTYPE html>[\s\S]*?</html>", "", html_str.strip(),re.S)
|
|
|
+ js_do_data = "".join(re.findall('};go\((.*?)\)', html_str))
|
|
|
+ js_func = re.sub("<(/*?)script>", "", html_str)
|
|
|
+ location = re.compile('location(.*?)}}else')
|
|
|
+ location2 = re.compile('location(.*?)}else')
|
|
|
+ setTimeout = re.compile('0x5dc;}}(.*?)setTimeout,function\(\)\{')
|
|
|
+ setTimeout2 = re.compile('0x5dc;}(.*?)setTimeout\(function\(\)\{')
|
|
|
+ gox = re.compile('};go(.*?)\)')
|
|
|
+ js_func = re.sub(location, "}}else", js_func)
|
|
|
+ js_func = re.sub(location2, "}else", js_func)
|
|
|
+ js_func = re.sub(setTimeout, "0x5dc;}}", js_func)
|
|
|
+ js_func = re.sub(setTimeout2, "0x5dc;}", js_func)
|
|
|
+ js_func = re.sub(gox, "return document['cookie']\n};", js_func)
|
|
|
+
|
|
|
+ js_func = '''const jsdom = require("jsdom");
|
|
|
+ const {JSDOM} = jsdom;
|
|
|
+ const dom = new JSDOM(`<!DOCTYPE html><p>Hello world</p>`,
|
|
|
+ {
|
|
|
+ url: "https://example.org/",
|
|
|
+ referrer: "https://example.com/",
|
|
|
+ contentType: "text/html",
|
|
|
+ });
|
|
|
+ window = dom.window;
|
|
|
+ document = window.document;
|
|
|
+ location = window.location;
|
|
|
+ ''' + js_func
|
|
|
+ ctx = execjs.compile(js_func)
|
|
|
+ # with open('ex_js.js', 'w+', encoding='utf-8') as f:
|
|
|
+ # f.write(js_func)
|
|
|
+ try:
|
|
|
+ ss = ctx.call("go", json.loads(js_do_data))
|
|
|
+ for item in ss.split(";"):
|
|
|
+ if '=' in item:
|
|
|
+ session.cookies.setdefault(item.split("=")[0], item.split("=")[-1])
|
|
|
+ session.get(start_url,headers=self.headers,timeout=120,verify=False)
|
|
|
+ cookies = requests.utils.dict_from_cookiejar(session.cookies)
|
|
|
+ return cookies
|
|
|
+ except Exception as e:
|
|
|
+ pass
|
|
|
+
|
|
|
+
|
