-1

提前抱歉占用您的时间，但我真的被阻止了！

我在 Python 中很牛，但我努力学习，我试图让这个脚本运行。它在没有线程的情况下工作，但为了学习和提高我的 python 技能，我想了解这出了什么问题！

问题： - 脚本永远不会结束 - 它没有解析任何东西...... urlopen 的东西似乎无法正常工作

非常感谢您的帮助，我还在努力:-)

import Queue
import threading
import urllib2
from urllib2 import urlopen
import time
from bs4 import BeautifulSoup as BeautifulSoup
import xlwt
import time
import socket

socket.setdefaulttimeout(20.0)


class Retry(object):
    default_exceptions = (Exception,)
    def __init__(self, tries, exceptions=None, delay=0):
        """
        Decorator for retrying a function if exception occurs

        tries -- num tries 
        exceptions -- exceptions to catch
        delay -- wait between retries
        """
        self.tries = tries
        if exceptions is None:
            exceptions = Retry.default_exceptions
        self.exceptions =  exceptions
        self.delay = delay

    def __call__(self, f):
        def fn(*args, **kwargs):
            exception = None
            for _ in range(self.tries):
                try:
                    return f(*args, **kwargs)
                except self.exceptions, e:
                    print "Retry, exception: "+str(e)
                    time.sleep(self.delay)
                    exception = e
            #if no success after tries, raise last exception
            raise exception
        return fn

@Retry(5)
def open_url(source):
    print("OPENING %s" % source)
    print("Retrying to open and read the page")
    resp = urlopen(source)
    resp = resp.read()
    return resp



queue = Queue.Queue()
out_queue = Queue.Queue()

class ThreadUrl(threading.Thread):
    """Threaded Url Grab"""
    def __init__(self, queue, out_queue):
        threading.Thread.__init__(self)
        self.queue = queue
        self.out_queue = out_queue

    def run(self):
        while True:
            #grabs host from queue
            host = self.queue.get()

            #grabs urls of hosts and then grabs chunk of webpage
            chunk = open_url(host)
            #chunk = url.read()

            #place chunk into out queue
            self.out_queue.put(chunk)

            #signals to queue job is done
            self.queue.task_done()

class DatamineThread(threading.Thread):
    """Threaded Url Grab"""
    def __init__(self, out_queue):
        threading.Thread.__init__(self)
        self.out_queue = out_queue

    def run(self):
        global x
        while True:
            #grabs host from queue
            chunk = self.out_queue.get()

            #parse the chunk
            soup = BeautifulSoup(chunk)
            #print soup
            tableau = soup.findAll('table')
        rows = tableau[1].findAll('tr')
            print("DONE")
        for tr in rows:
            cols = tr.findAll('td')
                y = 0
                x = x + 1
            for td in cols:
                    texte_bu = td.text
                    texte_bu = texte_bu.encode('utf-8')
            print texte_bu
                    ws.write(x,y,td.text)
                    y = y + 1
        wb.save("IA.xls")

            #signals to queue job is done
            self.out_queue.task_done()
            break

start = time.time()
def main():

    #spawn a pool of threads, and pass them queue instance
    for i in range(13):
        t = ThreadUrl(queue, out_queue)
        t.setDaemon(True)
        t.start()

    #populate queue with data
    for host in hosts:
        queue.put(host)

    for i in range(1):
        dt = DatamineThread(out_queue)
        dt.setDaemon(True)
        dt.start()


    #wait on the queue until everything has been processed
    queue.join()
    out_queue.join()


global x
x = 0

wb = xlwt.Workbook(encoding='utf-8')
ws = wb.add_sheet("BULATS_IA_PARSED")

Countries_List = ['Afghanistan','Armenia','Brazil','Argentina','Armenia','Australia','Austria','Azerbaijan','Bahrain','Bangladesh','Belgium','Belize','Bolivia','Bosnia and Herzegovina','Brazil','Brunei Darussalam','Bulgaria','Cameroon','Canada','Central African Republic','Chile','China','Colombia','Costa Rica','Croatia','Cuba','Cyprus','Czech Republic','Denmark','Dominican Republic','Ecuador','Egypt','Eritrea','Estonia','Ethiopia','Faroe Islands','Fiji','Finland','France','French Polynesia','Georgia','Germany','Gibraltar','Greece','Grenada','Hong Kong','Hungary','Iceland','India','Indonesia','Iran','Iraq','Ireland','Israel','Italy','Jamaica','Japan','Jordan','Kazakhstan','Kenya','Kuwait','Latvia','Lebanon','Libya','Liechtenstein','Lithuania','Luxembourg','Macau','Macedonia','Malaysia','Maldives','Malta','Mexico','Monaco','Montenegro','Morocco','Mozambique','Myanmar (Burma)','Nepal','Netherlands','New Caledonia','New Zealand','Nigeria','Norway','Oman','Pakistan','Palestine','Papua New Guinea','Paraguay','Peru','Philippines','Poland','Portugal','Qatar','Romania','Russia','Saudi Arabia','Serbia','Singapore','Slovakia','Slovenia','South Africa','South Korea','Spain','Sri Lanka','Sweden','Switzerland','Syria','Taiwan','Thailand','Trinadad and Tobago','Tunisia','Turkey','Ukraine','United Arab Emirates','United Kingdom','United States','Uruguay','Uzbekistan','Venezuela','Vietnam']
hosts = ["http://www.cambridgeesol.org/institutions/results.php?region=%s&type=&BULATS=on" % Countries for Countries in Countries_List]

main()

print "Elapsed Time: %s" % (time.time() - start)

PS：另外，你认为 urllib3 (keep-connexion) 在这种情况下有用吗？你能解释一下谁来实现它吗？

4

2 回答 2

1

脚本不会结束，因为 run 方法包含无限循环，没有什么可以让它们跳出这个循环

while True:
于 2012-04-24T09:18:28.740 回答
1

我必须承认我没有审查您发布的全部代码，但是“线程”和“urllib2”一起足以引起警报。

不要尝试将 urllib2 用于单线程同步连接之外的任何东西！不是因为 urllib2 有什么问题，而仅仅是因为这个问题已经解决了，而且解决方案在Twisted中，这是一个文档齐全且使用良好的 Python 异步网络库。

于 2012-04-24T03:49:08.300 回答