我正在编写一个 Python 网络爬虫,我想让它成为多线程的。现在我已经完成了基本部分,下面是它的作用:
一个线程从队列中获取一个 url;
线程从页面中提取链接,检查链接是否存在于池(一组)中,并将新链接放入队列和池中;
线程将 url 和 http 响应写入 csv 文件。
但是当我运行爬虫时,它最终总是卡住,不能正常退出。我已经浏览了 Python 的官方文档,但仍然没有任何线索。
下面是代码:
#!/usr/bin/env python
#!coding=utf-8
import requests, re, urlparse
import threading
from Queue import Queue
from bs4 import BeautifulSoup
#custom modules and files
from setting import config
class Page:
def __init__(self, url):
self.url = url
self.status = ""
self.rawdata = ""
self.error = False
r = ""
try:
r = requests.get(self.url, headers={'User-Agent': 'random spider'})
except requests.exceptions.RequestException as e:
self.status = e
self.error = True
else:
if not r.history:
self.status = r.status_code
else:
self.status = r.history[0]
self.rawdata = r
def outlinks(self):
self.outlinks = []
#links, contains URL, anchor text, nofollow
raw = self.rawdata.text.lower()
soup = BeautifulSoup(raw)
outlinks = soup.find_all('a', href=True)
for link in outlinks:
d = {"follow":"yes"}
d['url'] = urlparse.urljoin(self.url, link.get('href'))
d['anchortext'] = link.text
if link.get('rel'):
if "nofollow" in link.get('rel'):
d["follow"] = "no"
if d not in self.outlinks:
self.outlinks.append(d)
pool = Queue()
exist = set()
thread_num = 10
lock = threading.Lock()
output = open("final.csv", "a")
#the domain is the start point
domain = config["domain"]
pool.put(domain)
exist.add(domain)
def crawl():
while True:
p = Page(pool.get())
#write data to output file
lock.acquire()
output.write(p.url+" "+str(p.status)+"\n")
print "%s crawls %s" % (threading.currentThread().getName(), p.url)
lock.release()
if not p.error:
p.outlinks()
outlinks = p.outlinks
if urlparse.urlparse(p.url)[1] == urlparse.urlparse(domain)[1] :
for link in outlinks:
if link['url'] not in exist:
lock.acquire()
pool.put(link['url'])
exist.add(link['url'])
lock.release()
pool.task_done()
for i in range(thread_num):
t = threading.Thread(target = crawl)
t.start()
pool.join()
output.close()
任何帮助,将不胜感激!
谢谢
马库斯