多线程爬虫
多线程基础
import threading
多线程基础
import threading
class A(threading.Thread):
def __init__(self):
threading.Thread.__init__(self)
def run(self):
for i in range(10):
print("我是线程A")
class B(threading.Thread):
def __init__(self):
threading.Thread.__init__(self)
def run(self):
for i in range(10):
print("我是线程B")
t1 = A()
t2 = B()
t1.start()
t2.start()
队列基础
依次访问放入队列的url
import queue
a = queue.Queue()
a.put("hello")
a.task_done() #该次入队列任务完成
print(a.get())
多线程爬虫
线程1爬url并处理成真实url,放入队列urlqueue
线程2从urlqueue中取url爬对应信息
线程3判断程序是否完成,延迟60s执行
这段代码编码还有问题
import threading
import queue
import re
import urllib.request
import time
import urllib.error
urlqueue = queue.Queue()
headers = ("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36")
opener = urllib.request.build_opener()
opener.addheaders = [headers]
urllib.request.install_opener(opener) #将opener安装为全局
listurl = []
#使用代理服务器的函数
def use_proxy(proxy_addr, url):
try:
# proxy = urllib.request.ProxyHandler({'http':proxy_addr})
# opener = urllib.request.build_opener(proxy, urllib.request.HTTPHandler)
# urllib.request.install_opener(opener)
data = urllib.request.urlopen(url).read().decode('utf-8')
return data
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
time.sleep(10)
except Exception as e:
print("exception:" + str(e))
time.sleep(1)
#线程一,专门获取对应网址并处理为真实网址
class geturl(threading.Thread):
def __init__(self, key, pagestart, pageend, proxy, urlqueue):
threading.Thread.__init__(self)
self.pagestart = pagestart
self.pageend = pageend
self.proxy = proxy
self.urlqueue = urlqueue
self.key = key
def run(self):
page = self.pagestart
#编码关键词key
keycode = urllib.request.quote(self.key)
for page in range(self.pagestart, self.pageend+1):
url = "http://weixin.sogou.com/weixin?type=2&query="+keycode+"&page="+str(page)
data1 = use_proxy(self.proxy, url)
listurlpat = '<div class="txt-box">.*?(http://.*?)"'
listurl.append(re.compile(listurlpat, re.S).findall(data1))
#便于调试
print("获取到"+str(len(listurl))+"页")
for i in range(0, len(listurl)):
#等一等线程2,合理分配资源
time.sleep(7)
for j in range(0, len(listurl[i])):
try:
url = listurl[i][j]
#处理成真实url,读者亦可以观察对应网址的关系自行分析,采集网址比真实网址多了一串amp
url = url.replace("amp;","")
print("第"+str(i)+"i"+str(j)+"j次入队")
self.urlqueue.put(url)
self.urlqueue.task_done()
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
time.sleep(10)
except Exception as e:
print("exception:"+str(e))
time.sleep(1)
#线程2,与线程1并行执行,从线程1提供的文章网址中一次爬去对应文章信息并处理
class getcontent(threading.Thread):
def __init__(self, urlqueue, proxy):
threading.Thread.__init__(self)
self.urlqueue = urlqueue
self.proxy = proxy
def run(self):
html1='''<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>微信文章页面</title>
</head>
<body>'''
html2 = '''</body></html>'''
i = 1
while(True):
if not self.urlqueue.empty():
fh = open("../weixin/"+ str(i) +".html", "wb")
fh.write(html1.encode('utf-8'))
try:
url = self.urlqueue.get()
data = str(urllib.request.urlopen(url).read().decode('utf-8'))
titlepat = "<title>(.*?)</title>"
contentpat = 'id="js_content">(.*?)id="js_sg_bar"'
title = re.compile(titlepat).findall(data)
content = re.compile(contentpat).findall(data)
thistitle="此次没有获取到"
thiscontent = "此次没有获取到"
if(title != []):
thistitle = title[0]
if(content != []):
thiscontent = content[0]
dataall = "<p>标题为:"+thistitle+"</p><p>内容为:"+thiscontent+"</p><br>"
fh.write(dataall.encode('utf-8'))
print("第"+str(i)+"个页面处理") #便于调试
i += 1
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
time.sleep(10)
except Exception as e:
print("exceptioin:" + str(e))
time.sleep(1)
fh.write(html2.encode('utf-8'))
fh.close()
#并行控制程序 若60s未响应,并且存url的队列已空,则判断为执行成功
class conrl(threading.Thread):
def __init__(self, urlqueue):
threading.Thread.__init__(self)
self.urlqueue = urlqueue
def run(self):
while(True):
print("程序执行中")
time.sleep(60)
if(self.urlqueue.empty()):
print("程序执行完毕!")
exit()
key = "人工智能"
proxy = "101.236.35.98:8866"
proxy2 = ""
pagestart = 1
pageend = 2
t1 = geturl(key, pagestart, pageend, proxy, urlqueue)
t1.start()
t2 = getcontent(urlqueue, proxy)
t2.start()
t3 = conrl(urlqueue)
t3.start()