Python으로 웹사이트를 크롤링하기 위한 실용적인 팁

import urllib2
content = urllib2.urlopen('http://XXXX').read()

import urllib2
proxy_support = urllib2.ProxyHandler({'http':'http://XX.XX.XX.XX:XXXX'})
opener = urllib2.build_opener(proxy_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
content = urllib2.urlopen('http://XXXX').read()

import urllib2, cookielib
cookie_support= urllib2.HTTPCookieProcessor(cookielib.CookieJar())
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
content = urllib2.urlopen('http://XXXX').read()

opener = urllib2.build_opener(proxy_support, cookie_support, urllib2.HTTPHandler)

import urllib
postdata=urllib.urlencode({
 'username':'XXXXX',
 'password':'XXXXX',
 'continueURI':'http://www.verycd.com/',
 'fk':fk,
 'login_submit':'登录'
})

req = urllib2.Request(
 url = 'http://secure.verycd.com/signin/*///m.sbmmt.com/',
 data = postdata
)
result = urllib2.urlopen(req).read()

import urllib2
from gzip import GzipFile
from StringIO import StringIO
class ContentEncodingProcessor(urllib2.BaseHandler):
 """A handler to add gzip capabilities to urllib2 requests """
 
 # add headers to requests
 def http_request(self, req):
 req.add_header("Accept-Encoding", "gzip, deflate")
 return req
 
 # decode
 def http_response(self, req, resp):
 old_resp = resp
 # gzip
 if resp.headers.get("content-encoding") == "gzip":
  gz = GzipFile(
     fileobj=StringIO(resp.read()),
     mode="r"
     )
  resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
  resp.msg = old_resp.msg
 # deflate
 if resp.headers.get("content-encoding") == "deflate":
  gz = StringIO( deflate(resp.read()) )
  resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code) # 'class to add info() and
  resp.msg = old_resp.msg
 return resp
 
# deflate support
import zlib
def deflate(data): # zlib only provides the zlib compress format, not the deflate format;
 try:    # so on top of all there's this workaround:
 return zlib.decompress(data, -zlib.MAX_WBITS)
 except zlib.error:
 return zlib.decompress(data)

encoding_support = ContentEncodingProcessor
opener = urllib2.build_opener( encoding_support, urllib2.HTTPHandler )
 
#直接用opener打开网页，如果服务器支持gzip/defalte则自动解压缩
content = opener.open(url).read()

from twisted.web.client import getPage
from twisted.internet import reactor
 
links = [ 'http://www.verycd.com/topics/%d/'%i for i in range(5420,5430) ]
 
def parse_page(data,url):
 print len(data),url
 
def fetch_error(error,url):
 print error.getErrorMessage(),url
 
# 批量抓取链接
for url in links:
 getPage(url,timeout=5) \
  .addCallback(parse_page,url) \ #成功则调用parse_page方法
  .addErrback(fetch_error,url)  #失败则调用fetch_error方法
 
reactor.callLater(5, reactor.stop) #5秒钟后通知reactor结束程序
reactor.run()

f = Fetcher(threads=10) #设定下载线程数为10
for url in urls:
 f.push(url) #把所有url推入下载队列
while f.taskleft(): #若还有未完成下载的线程
 content = f.pop() #从下载完成队列中取出结果
 do_with(content) # 处理content内容

import urllib2
from threading import Thread,Lock
from Queue import Queue
import time
 
class Fetcher:
 def __init__(self,threads):
  self.opener = urllib2.build_opener(urllib2.HTTPHandler)
  self.lock = Lock() #线程锁
  self.q_req = Queue() #任务队列
  self.q_ans = Queue() #完成队列
  self.threads = threads
  for i in range(threads):
   t = Thread(target=self.threadget)
   t.setDaemon(True)
   t.start()
  self.running = 0
 
 def __del__(self): #解构时需等待两个队列完成
  time.sleep(0.5)
  self.q_req.join()
  self.q_ans.join()
 
 def taskleft(self):
  return self.q_req.qsize()+self.q_ans.qsize()+self.running
 
 def push(self,req):
  self.q_req.put(req)
 
 def pop(self):
  return self.q_ans.get()
 
 def threadget(self):
  while True:
   req = self.q_req.get()
   with self.lock: #要保证该操作的原子性，进入critical area
    self.running += 1
   try:
    ans = self.opener.open(req).read()
   except Exception, what:
    ans = ''
    print what
   self.q_ans.put((req,ans))
   with self.lock:
    self.running -= 1
   self.q_req.task_done()
   time.sleep(0.1) # don't spam
 
if __name__ == "__main__":
 links = [ 'http://www.verycd.com/topics/%d/'%i for i in range(5420,5430) ]
 f = Fetcher(threads=10)
 for url in links:
  f.push(url)
 while f.taskleft():
  url,content = f.pop()
  print url,len(content)

from threading import stack_size
stack_size(32768*16)

 def get(self,req,retries=3):
  try:
   response = self.opener.open(req)
   data = response.read()
  except Exception , what:
   print what,req
   if retries>0:
    return self.get(req,retries-1)
   else:
    print 'GET Failed',req
    return ''
  return data

 import socket
 socket.setdefaulttimeout(10) #设置10秒后连接超时

def login(self,username,password):
 import urllib
 data=urllib.urlencode({'username':username,
       'password':password,
       'continue':'http://www.verycd.com/',
       'login_submit':u'登录'.encode('utf-8'),
       'save_cookie':1,})
 url = 'http://www.verycd.com/signin'
 self.opener.open(url,data).read()