# coding:utf-8
import time
import urllib2
import random
from bs4 import BeautifulSoup

def filter(tag):
    if cmp(tag.name, 'img') == 0:
        if tag.has_attr('class'):
            if cmp(tag['class'][0], 'lazy' == 0):
                return True

outfile = open("./20160717/avatar.txt", "a")

for i in range(135, 1500):
    print i
    url = 'http://www.woyaogexing.com/touxiang/index_'+str(i)+'.html'
    response = urllib2.urlopen(url)
    data = response.read()
    soup = BeautifulSoup(data, "lxml")
    imgs = soup.find_all(filter)

    for img in imgs:
        outfile.write(img['src'] + ',' + str(random.randint(0, 1))+ '\n')
    time.sleep(0.5)

# coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding("utf-8")

import urllib2
from bs4 import BeautifulSoup

def filter(tag):#解析包含网名的标签
    if cmp(tag.name, "ul") == 0:
        if tag.has_attr("class"):
            if cmp(tag['class'][0], 'list') == 0:
                return True

outfile = open("./name.txt", "a")#输出文件

for i in range(55, 145):
    print i
    url = 'http://www.oicq88.com/nvsheng/'+str(i)+'.htm'
    response = urllib2.urlopen(url)#/nvsheng/可以替换为其他的
    data = response.read()
    soup = BeautifulSoup(data, "lxml")
    ul = soup.find_all(filter)
    ulsoup = BeautifulSoup(str(ul[0]), "lxml")
    lis = ulsoup.find_all("li")

    for li in lis:
        outfile.write(str(li.p.text)+'\n')