def get_ip():
page = 1
base_url = 'http://www.kuaidaili.com/proxylist/'
while page <= 10:
url = base_url + str(page)
data = getHtml(url)
soup = BeautifulSoup(data,'lxml')
for tr in soup.find_all('tr'):
ip = tr.contents[1].string
port = tr.contents[3].string
if 'IP' == ip:
continue
yield ip,port
page+=1
sleep(1)
def get_ip():
page = 1
base_url = 'http://www.kuaidaili.com/proxylist/'
while page <= 10:
url = base_url + str(page)
data = getHtml(url)
soup = BeautifulSoup(data, 'lxml')
for tr in soup.find_all('tr'):
ip = tr.contents[1].string
port = tr.contents[3].string
if 'IP' == ip:
continue
yield ip, port
page += 1
sleep(1)
__author__ = 'wangqi'
import re
from commen import getHtml
# -*- coding:utf-8 -*-
page = 1
initail_url = 'http://www.qiushibaike.com/hot/page/' + str(page)
html = getHtml(initail_url)
pattern = re.compile('<div.*?author">.*?<a.*?<img.*?>(.*?)</a>.*?<div.*?'+
'content">(.*?)<!--(.*?)-->.*?</div>(.*?)<div class="stats.*?class="number">(.*?)</i>',re.S)
items = re.findall(pattern,html)
for item in items:
haveImg = re.search("img",item[3])
if not haveImg:
print(item[0],item[1],item[2],item[4])
__author__ = 'wangqi'
import re
from commen import getHtml
# -*- coding:utf-8 -*-
page = 1
initail_url = 'http://www.qiushibaike.com/hot/page/' + str(page)
html = getHtml(initail_url)
pattern = re.compile(
'<div.*?author">.*?<a.*?<img.*?>(.*?)</a>.*?<div.*?' +
'content">(.*?)<!--(.*?)-->.*?</div>(.*?)<div class="stats.*?class="number">(.*?)</i>',
re.S)
items = re.findall(pattern, html)
for item in items:
haveImg = re.search("img", item[3])
if not haveImg:
print(item[0], item[1], item[2], item[4])
