罂粟花 发表于 2017-1-2 16:04

爬虫爬取xxoo妹子图咯

看着煎蛋网妹子图不错,就嘎嘎嘎,全部在下载下来慢慢欣赏~~~
避免封杀
使用代{过}{滤}理
爬取会有些慢,
看代码

检查代{过}{滤}理ip是否可用模块
import requests
import gevent
import re
from crawl import ua
from gevent import monkey
monkey.patch_all()


def chack(proxy,q):
    try:
      ip = proxy.split(':')
      port = proxy.split(':')
      proxies = {"http": "http://%s:%s" % (ip, port),
                   "https": "https://%s:%s" % (ip, port)}
      headers = ua()
      r = requests.get('http://jandan.net/', headers=headers, proxies=proxies, timeout=5)
      if r.ok:
            q.put(proxies)
            print q.qsize()
    except Exception, e:
      pass


def chack_run(q):
    url = 'http://www.66ip.cn/nmtq.php?getnum=10000&anonymoustype=3&proxytype=2&api=66ip'
    r = requests.get(url).text
    reip = re.compile(r'(?<![\.\d])(?:\d{1,3}\.){3}\d{1,3}(?![\.\d]):\d{2,5}')
    tasks = reip.findall(r)
    spawns = []
    for task in tasks:
      spawns.append(gevent.spawn(chack,task,q))
    gevent.joinall(spawns)




爬取下载模块
import requests
import gevent
import random
import time
import os
from lxml import etree
from gevent import monkey
monkey.patch_all()

def ua():
    USER = [
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
      "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
      "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
      "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
      "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
      "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
      "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
      "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
      "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
      "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
      "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
      "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
      "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
      "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
      "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
      "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
      "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
      "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
      "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
      "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
      "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
      "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
      "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
      "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
      "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
    ]
    headers = {'User-Agent': random.choice(USER)}
    return headers


def crawl(url,q):
    print 'crawl'
    headers = ua()
    while q.empty():
      print 'ip proxy is empty'
      time.sleep(20)
    proxies = q.get()
    try:
      r = requests.get(url, headers=headers, proxies=proxies,timeout=5).content
      sel = etree.HTML(r)
      q.put(proxies)
      pngs = sel.xpath('//img/@src')
      for png in pngs:
            if 'http:' not in png:
                png = 'http:' + png
            r = requests.get(png, headers=headers).content
            if not os.path.exists('meizi'):
                os.mkdir('meizi')
            name = png.split('/')[-1]
            print name
            dir = 'meizi/' + name
            with open(dir, 'wb') as code:
                code.write(r)

    except Exception, e:
      pass

def crawl_run(q):
    spawns = []
    for ur in ['http://jandan.net/ooxx/page-%s#comments'% n for n in range(2299)]:
      spawns.append(gevent.spawn(crawl,ur,q))
    gevent.joinall(spawns)



run开始运行
from multiprocessing import Process,Queue
from chack import chack_run
from crawl import crawl_run

if __name__=="__main__":
    q = Queue()
    p1 = Process(target=chack_run,args=(q,))
    p2 = Process(target=crawl_run,args=(q,))
    p1.start()
    p2.start()


xiaoxinjian 发表于 2017-1-2 17:45

lkjlkjhong 发表于 2017-1-2 16:46
看到广大网友一致征求成品,我不由想起了不想要渔而要鱼的故事

我看到渔夫钓了几条鱼,看起来不错,我想尝尝,就问:渔夫,给我条鱼尝尝怎么样啊?渔夫:不行,不过我可以教你怎么钓鱼,你要学吗?我:哦,不了,我只想尝尝那条鱼罢了,我还得赶回去种地呢。

suantia 发表于 2017-1-2 16:21

樓主請問哈這個拿來干撒子滴?

kumwingchiu 发表于 2017-1-2 16:27

不懂,不懂

vocabulary 发表于 2017-1-2 16:30

好东西!谢谢分享!

q526840 发表于 2017-1-2 16:30

不明觉厉{:1_902:}

q245198004 发表于 2017-1-2 16:31

怎么用啊 楼主

桥段 发表于 2017-1-2 16:36


樓主請問哈這個拿來干撒子滴?

猫捉老虎 发表于 2017-1-2 16:39

不明觉厉,楼主有成品吗?怎么用?

52pojieYiHui 发表于 2017-1-2 16:45

这是什么语言的源码,不懂。也用不上

lkjlkjhong 发表于 2017-1-2 16:46

看到广大网友一致征求成品,我不由想起了不想要渔而要鱼的故事
页: [1] 2 3 4 5 6 7 8 9
查看完整版本: 爬虫爬取xxoo妹子图咯