Develop Reference

Python multiprocessing in for loop (requests and BeautifulSoup)

I have list of a lot of links and I want to use multiprocessing to speed the proccess, here is simplified version, I need it to be ordered like this:
I tried a lot of things, process, pool etc. I always had errors, I need to do it with 4 or 8 threads and make it ordered like this. Thank you for all help. Here is code:
from bs4 import BeautifulSoup
import requests
import time
links = ["http://www.tennisexplorer.com/match-detail/?id=1672704", "http://www.tennisexplorer.com/match-detail/?id=1699387", "http://www.tennisexplorer.com/match-detail/?id=1698990" "http://www.tennisexplorer.com/match-detail/?id=1696623", "http://www.tennisexplorer.com/match-detail/?id=1688719", "http://www.tennisexplorer.com/match-detail/?id=1686305"]
data = []
def essa(match, omega):
aaa = BeautifulSoup(requests.get(match).text, "lxml")
center = aaa.find("div", id="center")
p1_l = center.find_all("th", class_="plName")[0].find("a").get("href")
p2_l = center.find_all("th", class_="plName")[1].find("a").get("href")
return p1_l + " - " + p2_l + " - " + str(omega)
i = 1
start_time = time.clock()
for link in links:
data.append(essa(link, i))
i += 1
for d in data:
print(d)
print(time.clock() - start_time, "seconds")

Spawn several threads of the function and join them together:
from threading import Thread
def essa(match, omega):
aaa = BeautifulSoup(requests.get(match).text, "lxml")
center = aaa.find("div", id="center")
p1_l = center.find_all("th", class_="plName")[0].find("a").get("href")
p2_l = center.find_all("th", class_="plName")[1].find("a").get("href")
print p1_l + " - " + p2_l + " - " + str(omega)
if __name__ == '__main__':
threadlist = []
for index, url in enumerate(links):
t= Thread(target=essa,args=(url, index))
t.start()
threadlist.append(t)
for b in threadlist:
b.join()
You wont get them to print in order, for the simple reason that some http responses take longer than others.

As far I can understand you have the list of links and make requests concurrently to make the process faster. Here is the sample code for multithreading. I hope this will help you. Read the documentation for concurrent futures.
import concurrent.futures
import urllib.request
URLS = ['http://www.foxnews.com/',
'http://www.cnn.com/',
'http://europe.wsj.com/',
'http://www.bbc.co.uk/',
'http://some-made-up-domain.com/']
# Retrieve a single page and report the URL and contents
def load_url(url, timeout):
with urllib.request.urlopen(url, timeout=timeout) as conn:
return conn.read()
# We can use a with statement to ensure threads are cleaned up promptly
with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
# Start the load operations and mark each future with its URL
future_to_url = {executor.submit(load_url, url, 60): url for url in URLS}
for future in concurrent.futures.as_completed(future_to_url):
url = future_to_url[future]
try:
data = future.result()
except Exception as exc:
print('%r generated an exception: %s' % (url, exc))
else:
print('%r page is %d bytes' % (url, len(data)))

Python multiprocess Process never terminates

My routine below takes a list of urllib2.Requests and spawns a new process per request and fires them off. The purpose is for asynchronous speed, so it's all fire-and-forget (no response needed). The issue is that the processes spawned in the code below never terminate. So after a few of these the box wilL OOM. Context: Django web app. Any help?
MP_CONCURRENT = int(multiprocessing.cpu_count()) * 2
if MP_CONCURRENT < 2: MP_CONCURRENT = 2
MPQ = multiprocessing.JoinableQueue(MP_CONCURRENT)
def request_manager(req_list):
try:
# put request list in the queue
for req in req_list:
MPQ.put(req)
# call processes on queue
worker = multiprocessing.Process(target=process_request, args=(MPQ,))
worker.daemon = True
worker.start()
# move on after queue is empty
MPQ.join()
except Exception, e:
logging.error(traceback.print_exc())
# prcoess requests in queue
def process_request(MPQ):
try:
while True:
req = MPQ.get()
dr = urllib2.urlopen(req)
MPQ.task_done()
except Exception, e:
logging.error(traceback.print_exc())

Maybe i am not right, but
MP_CONCURRENT = int(multiprocessing.cpu_count()) * 2
if MP_CONCURRENT < 2: MP_CONCURRENT = 2
MPQ = multiprocessing.JoinableQueue(MP_CONCURRENT)
def request_manager(req_list):
try:
# put request list in the queue
pool=[]
for req in req_list:
MPQ.put(req)
# call processes on queue
worker = multiprocessing.Process(target=process_request, args=(MPQ,))
worker.daemon = True
worker.start()
pool.append(worker)
# move on after queue is empty
MPQ.join()
# Close not needed processes
for p in pool: p.terminate()
except Exception, e:
logging.error(traceback.print_exc())
# prcoess requests in queue
def process_request(MPQ):
try:
while True:
req = MPQ.get()
dr = urllib2.urlopen(req)
MPQ.task_done()
except Exception, e:
logging.error(traceback.print_exc())

MP_CONCURRENT = int(multiprocessing.cpu_count()) * 2
if MP_CONCURRENT < 2: MP_CONCURRENT = 2
MPQ = multiprocessing.JoinableQueue(MP_CONCURRENT)
CHUNK_SIZE = 20 #number of requests sended to one process.
pool = multiprocessing.Pool(MP_CONCURRENT)
def request_manager(req_list):
try:
# put request list in the queue
responce=pool.map(process_request,req_list,CHUNK_SIZE) # function exits after all requests called and pool work ended
# OR
responce=pool.map_async(process_request,req_list,CHUNK_SIZE) #function request_manager exits after all requests passed to pool
except Exception, e:
logging.error(traceback.print_exc())
# prcoess requests in queue
def process_request(req):
dr = urllib2.urlopen(req)
This works ~5-10x faster then your code

Integrate side "brocker" to django (such as rabbitmq or something like it).

Ok after some fiddling (and a good night's sleep) I believe I've figured out the problem (and thank you Eri, you were the inspiration I needed). The main issue of the zombie processes was that I was not signaling back that the process was finished (and killing it) both of which I (naively) thought was happening automagically with multiprocess.
The code that worked:
# function that will be run through the pool
def process_request(req):
try:
dr = urllib2.urlopen(req, timeout=30)
except Exception, e:
logging.error(traceback.print_exc())
# process killer
def sig_end(r):
sys.exit()
# globals
MP_CONCURRENT = int(multiprocessing.cpu_count()) * 2
if MP_CONCURRENT < 2: MP_CONCURRENT = 2
CHUNK_SIZE = 20
POOL = multiprocessing.Pool(MP_CONCURRENT)
# pool initiator
def request_manager(req_list):
try:
resp = POOL.map_async(process_request, req_list, CHUNK_SIZE, callback=sig_end)
except Exception, e:
logging.error(traceback.print_exc())
A couple of notes:
1) The function that will be hit by "map_async" ("process_request" in this example) must be defined first (and before the global declarations).
2) There is probably a more graceful way to exit the process (suggestions welcome).
3) Using pool in this example really was best (thanks again Eri) due to the "callback" feature which allows me to throw a signal right away.

process stop working while queue is not empty

I try to write a script in python to convert url into its corresponding ip. Since the url file is huge (nearly 10GB), so I'm trying to use multiprocessing lib.
I create one process to write output to file and a set of processes to convert url.
Here is my code:
import multiprocessing as mp
import socket
import time
num_processes = mp.cpu_count()
sentinel = None
def url2ip(inqueue, output):
v_url = inqueue.get()
print 'v_url '+v_url
try:
v_ip = socket.gethostbyname(v_url)
output_string = v_url+'|||'+v_ip+'\n'
except:
output_string = v_url+'|||-1'+'\n'
print 'output_string '+output_string
output.put(output_string)
print output.full()
def handle_output(output):
f_ip = open("outputfile", "a")
while True:
output_v = output.get()
if output_v:
print 'output_v '+output_v
f_ip.write(output_v)
else:
break
f_ip.close()
if __name__ == '__main__':
output = mp.Queue()
inqueue = mp.Queue()
jobs = []
proc = mp.Process(target=handle_output, args=(output, ))
proc.start()
print 'run in %d processes' % num_processes
for i in range(num_processes):
p = mp.Process(target=url2ip, args=(inqueue, output))
jobs.append(p)
p.start()
for line in open('inputfile','r'):
print 'ori '+line.strip()
inqueue.put(line.strip())
for i in range(num_processes):
# Send the sentinal to tell Simulation to end
inqueue.put(sentinel)
for p in jobs:
p.join()
output.put(None)
proc.join()
However, it did not work. It did produce several outputs (4 out of 10 urls in the test file) but it just suddenly stops while queues are not empty (I did check queue.empty())
Could anyone suggest what's wrong?Thanks

You're workers exit after processing a single url each, they need to loop internally until they get the sentinel. However, you should probably just look at multiprocessing.pool instead, as that does the bookkeeping for you.

Multi-threaded Python Web Crawler Got Stuck

I'm writing a Python web crawler and I want to make it multi-threaded. Now I have finished the basic part, below is what it does:
a thread gets a url from the queue;
the thread extracts the links from the page, checks if the links exist in a pool (a set), and puts the new links to the queue and the pool;
the thread writes the url and the http response to a csv file.
But when I run the crawler, it always gets stuck eventually, not exiting properly. I have gone through the official document of Python but still have no clue.
Below is the code:
#!/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()
Any help would be appreciated!
Thanks
Marcus

Your crawl function has an infinite while loop with no possible exit path.
The condition True always evaluates to True and the loop continues, as you say,
not exiting properly
Modify the crawl function's while loop to include a condition. For instance, when the number of links saved to the csv file exceeds a certain minimum number, then exit the while loop.
i.e.,
def crawl():
while len(exist) <= min_links:
...

Threads not stop in python

The purpose of my program is to download files with threads. I define the unit, and using len/unit threads, the len is the length of the file which is going to be downloaded.
Using my program, the file can be downloaded, but the threads are not stopping. I can't find the reason why.
This is my code...
#! /usr/bin/python
import urllib2
import threading
import os
from time import ctime
class MyThread(threading.Thread):
def __init__(self,func,args,name=''):
threading.Thread.__init__(self);
self.func = func;
self.args = args;
self.name = name;
def run(self):
apply(self.func,self.args);
url = 'http://ubuntuone.com/1SHQeCAQWgIjUP2945hkZF';
request = urllib2.Request(url);
response = urllib2.urlopen(request);
meta = response.info();
response.close();
unit = 1000000;
flen = int(meta.getheaders('Content-Length')[0]);
print flen;
if flen%unit == 0:
bs = flen/unit;
else :
bs = flen/unit+1;
blocks = range(bs);
cnt = {};
for i in blocks:
cnt[i]=i;
def getStr(i):
try:
print 'Thread %d start.'%(i,);
fout = open('a.zip','wb');
fout.seek(i*unit,0);
if (i+1)*unit > flen:
request.add_header('Range','bytes=%d-%d'%(i*unit,flen-1));
else :
request.add_header('Range','bytes=%d-%d'%(i*unit,(i+1)*unit-1));
#opener = urllib2.build_opener();
#buf = opener.open(request).read();
resp = urllib2.urlopen(request);
buf = resp.read();
fout.write(buf);
except BaseException:
print 'Error';
finally :
#opener.close();
fout.flush();
fout.close();
del cnt[i];
# filelen = os.path.getsize('a.zip');
print 'Thread %d ended.'%(i),
print cnt;
# print 'progress : %4.2f'%(filelen*100.0/flen,),'%';
def main():
print 'download at:',ctime();
threads = [];
for i in blocks:
t = MyThread(getStr,(blocks[i],),getStr.__name__);
threads.append(t);
for i in blocks:
threads[i].start();
for i in blocks:
# print 'this is the %d thread;'%(i,);
threads[i].join();
#print 'size:',os.path.getsize('a.zip');
print 'download done at:',ctime();
if __name__=='__main__':
main();
Could someone please help me understand why the threads aren't stopping.

I can't really address your code example because it is quite messy and hard to follow, but a potential reason you are seeing the threads not end is that a request will stall out and never finish. urllib2 allows you to specify timeouts for how long you will allow the request to take.
What I would recommend for your own code is that you split your work up into a queue, start a fixed number of thread (instead of a variable number), and let the worker threads pick up work until it is done. Make the http requests have a timeout. If the timeout expires, try again or put the work back into the queue.
Here is a generic example of how to use a queue, a fixed number of workers and a sync primitive between them:
import threading
import time
from Queue import Queue
def worker(queue, results, lock):
local_results = []
while True:
val = queue.get()
if val is None:
break
# pretend to do work
time.sleep(.1)
local_results.append(val)
with lock:
results.extend(local_results)
print threading.current_thread().name, "Done!"
num_workers = 4
threads = []
queue = Queue()
lock = threading.Lock()
results = []
for i in xrange(100):
queue.put(i)
for _ in xrange(num_workers):
# Use None as a sentinel to signal the threads to end
queue.put(None)
t = threading.Thread(target=worker, args=(queue,results,lock))
t.start()
threads.append(t)
for t in threads:
t.join()
print sorted(results)
print "All done"