xurenlu

//
//  main.m
//  xtt
//
//  Created by r on 14-10-9.
//  Copyright (c) 2014年 r. All rights reserved.
//

#import <Foundation/Foundation.h>
#import <Cocoa/Cocoa.h>

xurenlu

class MySpider(BaseSpider):
    name = 'myspider'
    start_urls = (
        'http://example.com/page1',
        'http://example.com/page2',
        )

    def parse(self, response):
        # collect `item_urls`
        for item_url in item_urls:

xurenlu

from threading import Thread,Condition,currentThread
import time,sys,os,signal
import random
from subprocess import *
from BaseHTTPServer import *
from urlparse import urlparse
from urlparse import parse_qs
import  urllib
import json
from ghost import Ghost

xurenlu

<?php
/** vim:set foldmethod=marker: */
/**
 * @author renlu<helloasp@hotmail.com>
 * @version 1.0.0
 * @mail xurenlu@gmail.com
 * @homepage http://www.162cm.com/
 * */
//require "./phpQuery-onefile.php";
mb_internal_encoding("UTF-8");

xurenlu

<?php
/** vim:set foldmethod=marker: */
/**
 * @author renlu<helloasp@hotmail.com>
 * @version 1.0.0
 * @mail xurenlu@gmail.com
 * @homepage http://www.162cm.com/
 * */
//require "./phpQuery-onefile.php";
mb_internal_encoding("UTF-8");

xurenlu

<?php
//update: support 

$url= empty($_GET["url"])?$_SERVER["QUERY_STRING"]:$_GET["url"];
if(preg_match('/^http:\/\/.*/',$url)==false) die();
echo curl_fetch($url);
function curl_fetch($url, $timeout=30){
    global $CONFIG,$MODULES;

	

xurenlu

from scrapy.http import Request, FormRequest, HtmlResponse

import gtk
import webkit
import jswebkit
import settings

class WebkitDownloader( object ):
    def process_request( self, request, spider ):
        if spider.name in settings.WEBKIT_DOWNLOADER:

xurenlu

from scrapy.http import Request, FormRequest, HtmlResponse

import gtk
import webkit
import jswebkit
import settings

class WebkitDownloader( object ):
    def process_request( self, request, spider ):
        if spider.name in settings.WEBKIT_DOWNLOADER:

xurenlu

import os, cookielib, urllib2
cj = cookielib.MozillaCookieJar()
cj.load("./ck2")
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
params = {'domain':"www.renren.com",'origURL':"http://www.renren.com/PLogin.do",'email':"xurenlu@126.com", 'password':"842519"}
req = urllib2.Request(  
            'http://www.renren.com/PLogin.do'
            #
        )

xurenlu

from cookielib import CookieJar as _CookieJar, DefaultCookiePolicy

#from scrapy.utils.httpobj import urlparse_cached

def sqlite2cookie():#filename
   from cStringIO import StringIO
   #from pysqlite2 import dbapi2 as sqlite
   import sqlite3
   import cookielib