python爬虫的一个常见简单js反爬详解

< script type = "text/javascript" >
function stringToHex(str) {
  var val = "";
  for (var i = 0; i < str.length; i++) {
    if (val == "") val = str.charCodeAt(i).toString(16);
    else val += str.charCodeAt(i).toString(16);
  }
  return val;
}
function YunSuoAutoJump() {
  var width = screen.width;
  var height = screen.height;
  var screendate = width + "," + height;
  var curlocation = window.location.href;
  if ( - 1 == curlocation.indexOf("security_verify_")) {
    document.cookie = "srcurl=" + stringToHex(window.location.href) + ";path=/;";
  }
  self.location = "/archives/category/jk" + stringToHex(screendate);
} < /script>
 <script>setTimeout("YunSuoAutoJump()", 50);</script > 

def stringToHex(string):
  length = len(string)
  hex_string = str()
  for i in xrange(length):
    hex_string += hex(ord(string[i]))[2:]
  return hex_string

def get_cookie(url):
  hex_string = stringToHex(url)
  cookie = {"srcurl": hex_string, "path": "/"}
  return cookie

url = "http://www.hnrexian.com/archives/category/jk"
s = requests.Session()
r = s.get(url)
url_2 = re.compile("self\.location\s*=\s*\"(.*"").findall(r.text)[0]
screen_date = "1920,1080"
url_2 = url_2 + stringToHex(screen_date)
url_2 = urljoin(url, url_2)
cookie = get_cookie(url)
s.cookies.update(cookie)
r2 = s.get(url_2)
url3 = re.compile("self\.location\s*=\s*\"(.*"").findall(r2.text)[0]
r3 = s.get(url3)
r3.encoding = "gbk"
print r3.text