cuimuxi

回民吃猪肉
习近平
TMD
毛民进党
妹妹淫水 流
机吧
联国
1989六四
性爱电影
李红智

cuimuxi

select fans_id from messages where content in ('形勢', '形式', '形势') and mp_id=35164 and created_time >= '2014-07-24 06:00:00' and created_time < '2014-07-24 07:00:00'group by fans_id

cuimuxi

"""
This is a simple example of WebSocket + Tornado + Redis Pub/Sub usage.
Do not forget to replace YOURSERVER by the correct value.
Keep in mind that you need the *very latest* version of your web browser.
You also need to add Jacob Kristhammar's websocket implementation to Tornado:
Grab it here:
    http://gist.github.com/526746
Or clone my fork of Tornado with websocket included:
    http://github.com/pelletier/tornado
Oh and the Pub/Sub protocol is only available in Redis 2.0.0:

cuimuxi

from scrapy import log
from scrapy.item import Item
from scrapy.http import Request
from scrapy.contrib.spiders import XMLFeedSpider


def NextURL():
    """
    Generate a list of URLs to crawl. You can query a database or come up with some other means
    Note that if you generate URLs to crawl from a scraped URL then you're better of using a 

cuimuxi

#!/usr/bin/env python
#
# Copyright 2009 Facebook
#
# Licensed under the Apache License, Version 2.0 (the "License"); you may
# not use this file except in compliance with the License. You may obtain
# a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#

cuimuxi

import os
import shutil
import subprocess
import sys
import tarfile
import urllib2

LIBXML2_PREFIX = "libxml2"
LIBXSLT_PREFIX = "libxslt"
LIBXML2_FTPURL = "ftp://xmlsoft.org/libxml2/"

cuimuxi

from gcrawler import GCrawler, Downloader
import unittest
import urllib2
import logging
import traceback
from datetime import datetime
import re

logging.basicConfig(level=logging.DEBUG)

cuimuxi

import gevent
from gevent import monkey, queue

monkey.patch_all()

import urllib2
from time import sleep
import traceback
import logging

cuimuxi

# -*- coding:utf-8 -*-
import re
import urllib2
from lib.BeautifulSoup import BeautifulSoup

agent="""Sosospider+(+http://help.soso.com/webspider.htm)"""

blog_url = 'http://blog.sina.com.cn/s/articlelist_1517582220_0_1.html'
spider_handle = urllib2.urlopen(blog_url)
blog_content = spider_handle.read()