Develop Reference

How to properly debug ThreadPool?

I'm trying to get some data from a web page. To speed up this process (they allow me to make 1000 requests per minute), I use ThreadPool.
Since there is a huge amount of data, the process is quite vulnerable to connection fails etc. so I try to log everything I can to be able to detect each mistake I did in code.
The problem is that program sometimes just stops without any exception (it acts like it is running but with no effect - I use PyCharm). I log catched exceptions everywhere I can but I can't see any exception in any log.
I assume that if there were a timeout reached, the exception would be raised and logged.
I've found out where the problem could be. Here is the code:
As a pool, I use: from multiprocessing.pool import ThreadPool as Pool
And lock: from threading import Lock
The download_category function is being used in loop.
def download_category(url):
# some code
#
# ...
log('Create pool...')
_pool = Pool(_workers_number)
with open('database/temp_produkty.txt') as f:
log('Spracovavanie produktov... vytvaranie vlakien...') # I see this in log
for url_product in f:
x = _pool.apply_async(process_product, args=(url_product.strip('\n'), url))
_pool.close()
_pool.join()
log('Presuvanie produktov z temp export do export.csv...') # I can't see this in log
temp_export_to_export_csv()
set_spracovanie_kategorie(url)
except Exception as e:
logging.exception('Got exception on download_one_category: {}'.format(url))
And process_product function:
def process_product(url, cat):
try:
data = get_product_data(url)
except:
log('{}: {} exception while getting product data... #') # I don't see this in log
return
try:
print_to_temp_export(data, cat) # I don't see this in log
except:
log('{}: {} exception while printing to csv... #') # I don't see this in log
raise
LOG function:
def log(text):
now = datetime.now().strftime('%d.%m.%Y %H:%M:%S')
_lock.acquire()
mLib.printToFile('logging/log.log', '{} -> {}'.format(now, text))
_lock.release()
I use logging module too. In this log, I see that probably 8 (number of workers) times request was sent but no answer hasn't been recieved.
EDIT1:
def get_product_data(url):
data = defaultdict(lambda: '-')
root = load_root(url)
try:
nazov = root.xpath('//h1[#itemprop="name"]/text()')[0]
except:
nazov = root.xpath('//h1/text()')[0]
under_block = root.xpath('//h2[#id="lowest-cost"]')
if len(under_block) < 1:
under_block = root.xpath('//h2[contains(text(),"Naj")]')
if len(under_block) < 1:
return False
data['nazov'] = nazov
data['url'] = url
blocks = under_block[0].xpath('./following-sibling::div[#class="shp"]/div[contains(#class,"shp")]')
i = 0
for block in blocks:
i += 1
data['dat{}_men'.format(i)] = eblock.xpath('.//a[#class="link"]/text()')[0]
del root
return data
LOAD ROOT:
class RedirectException(Exception):
pass
def load_url(url):
r = requests.get(url, allow_redirects=False)
if r.status_code == 301:
raise RedirectException
if r.status_code == 404:
if '-q-' in url:
url = url.replace('-q-','-')
mLib.printToFileWOEncoding('logging/neexistujuce.txt','Skusanie {} kategorie...'.format(url))
return load_url(url) # THIS IS NOT LOOPING
else:
mLib.printToFileWOEncoding('logging/neexistujuce.txt','{}'.format(url))
html = r.text
return html
def load_root(url):
try:
html = load_url(url)
except Exception as e:
logging.exception('load_root_exception')
raise
return etree.fromstring(html, etree.HTMLParser())

Python - Multithreaded Proxy Tester

I'm building a proxy checker using multithreads, specificly a thread pool from:
from multiprocessing.dummy import Pool as ThreadPool.
The http request is by using urllib2.
What I want to do is for each proxy run 20 requests. If it was 1 threaded it would take too much time. thats where the multithreads power comes to help. So once I set up the proxy I want to run those 20 requests, and manage 2 things. One is to count the exceptions and dump the proxy if too many occurs. 2nd Is to save the average response time and present it later.
I just don't manage to implement the above. But I have implemented it with 1 thread:
import socket
import ssl
import time
import urllib
import urllib2
import httplib
proxyList = []
def loadProxysFromFile(fileName):
global proxyList
with open(fileName) as f:
proxyList = [line.rstrip('\n') for line in f]
def setUrllib2Proxy(proxyAddress):
proxy = urllib2.ProxyHandler({
'http': "http://" + proxyAddress,
'https': "https://" + proxyAddress
})
opener = urllib2.build_opener(proxy)
urllib2.install_opener(opener)
def timingRequest(proxy, url):
error = False
setUrllib2Proxy(proxy)
start = time.time()
try:
req = urllib2.Request(url)
urllib2.urlopen(req, timeout=5) #opening the request (getting a response)
except (urllib2.URLError, httplib.BadStatusLine, ssl.SSLError, socket.error) as e:
error = True
end = time.time()
timing = end - start
if error:
print "Error with proxy " + proxy
return 0
else:
print proxy + " Request to " + url + " took: %s" %timing + " seconds."
return timing
# Main
loadProxysFromFile("proxyList.txt")
for proxy in proxyList:
print "Testing: " + proxy
print "\n"
REQUEST_NUM = 20
ERROR_TOLERANCE_NUM = 3
resultList = []
for proxy in proxyList:
avgTime = 0
errorCount = 0
for x in range(0, REQUEST_NUM):
result = timingRequest(proxy, 'https://www.google.com')
if (result == 0):
errorCount += 1
if (errorCount >= ERROR_TOLERANCE_NUM):
break
else:
avgTime += result
if (errorCount < ERROR_TOLERANCE_NUM):
avgTime = avgTime/(REQUEST_NUM-errorCount)
resultList.append(proxy + " has an average response time of: %s" %avgTime)
print '\n'
print "Results Summery: "
print "-----------------"
for res in resultList:
print res
Things that must be done are:
for every proxy: wait until all 20 requests are over before changing proxy. Sync somehow the threads when they adding up to calculate the average response time (includes not to take in account the exceptions)
The best solutions I've read so far is using from multiprocessing.dummy import Pool as ThreadPool and pool.map(func, iterable) but I cant figure out how to implement it in my code.

Python, send a stop notification to a blocking loop within a thread

I've read many answers, however I have not found a proper solution.
The problem, I'm reading mixed/replace HTTP streams that will not expire or end by default.
You can try it by yourself using curl:
curl http://agent.mtconnect.org/sample\?interval\=0
So, now I'm using Python threads and requests to read data from multiple streams.
import requests
import uuid
from threading import Thread
tasks = ['http://agent.mtconnect.org/sample?interval=5000',
'http://agent.mtconnect.org/sample?interval=10000']
thread_id = []
def http_handler(thread_id, url, flag):
print 'Starting task %s' % thread_id
try:
requests_stream = requests.get(url, stream=True, timeout=2)
for line in requests_stream.iter_lines():
if line:
print line
if flag and line.endswith('</MTConnectStreams>'):
# Wait until XML message end is reached to receive the full message
break
except requests.exceptions.RequestException as e:
print('error: ', e)
except BaseException as e:
print e
if __name__ == '__main__':
for task in tasks:
uid = str(uuid.uuid4())
thread_id.append(uid)
t = Thread(target=http_handler, args=(uid, task, False), name=uid)
t.start()
print thread_id
# Wait Time X or until user is doing something
# Send flag = to desired thread to indicate the loop should stop after reaching the end.
Any suggestions? What is the best solution? I don't want to kill the thread because I would like to read the ending to have a full XML message.

I found a solution by using threading module and threading.events. Maybe not the best solution, but it works fine currently.
import logging
import threading
import time
import uuid
import requests
logging.basicConfig(level=logging.DEBUG, format='(%(threadName)-10s) %(message)s', )
tasks = ['http://agent.mtconnect.org/sample?interval=5000',
'http://agent.mtconnect.org/sample?interval=10000']
d = dict()
def http_handler(e, url):
logging.debug('wait_for_event starting')
message_buffer = []
filter_namespace = True
try:
requests_stream = requests.get(url, stream=True, timeout=2)
for line in requests_stream.iter_lines():
if line:
message_buffer.append(line)
if e.isSet() and line.endswith('</MTConnectStreams>'):
logging.debug(len(message_buffer))
break
except requests.exceptions.RequestException as e:
print('error: ', e)
except BaseException as e:
print e
if __name__ == '__main__':
logging.debug('Waiting before calling Event.set()')
for task in tasks:
uid = str(uuid.uuid4())
e = threading.Event()
d[uid] = {"stop_event": e}
t = threading.Event(uid)
t = threading.Thread(name=uid,
target=http_handler,
args=(e, task))
t.start()
logging.debug('Waiting 3 seconds before calling Event.set()')
for key in d:
time.sleep(3)
logging.debug(threading.enumerate())
logging.debug(d[key])
d[key]['stop_event'].set()
logging.debug('bye')

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:
...

Python Threading Error when executing a MSSQL statement

I have a producer, consumer application where the producer reads a database and puts the results into a website. On success, The consumer then gets the id of the transaction and updates the db.
The program runs as required until it attempts to execute the update. It fails sometimes with this error 'HY000', 'The driver did not supply an error!'
The code can comfortably write to file without any issues.
What could i do to fix this? We need to update the db.
Thanks
Notes...using python 2.7 with pyodbc on mssql 2008.
code below
#!/usr/bin/env python
from urlparse import urlparse
from threading import Thread
import httplib, sys
import Queue
import urllib2
import urllib
from time import localtime, strftime
from ConfigParser import SafeConfigParser
from functions import Functions
from pyodbcclass import db_mssql
now = strftime("%y-%m-%d-%H%M%S", localtime())
k = db_mssql()
thread_list = []
thread_list2 = []
getFromDBQueue = Queue.Queue()
updateDBQueue = Queue.Queue()
number_of_consumer_threads = 3
def putURL():
querySql = "select distinct top 3 id,url from tblURL where processed=0 order by id asc"
re = k.query2(querySql)
if re:
for r in re:
id = r.id
params = urllib.urlencode({'user': user, 'password': password})
ourl = urlini + "?%s" % params
urlplusid = {'url':ourl.strip(),'id':id}
getFromDBQueue.put(urlplusid)
def getURL(thread_id):
while 1:
try:
URL_toget = getFromDBQueue.get(block=False)
url2 = URL_toget['url']
msgid2 = URL_toget['id']
except Queue.Empty:
print "thread exiting, id: " + str(thread_id) + "++getFromDB++"
sys.exit()
status,url = getStatus(url2)
if status == 200:
updateDBQueue.put(msgid2)
print(status)
def updateDB(thread_id):
while 1:
try:
id2 = updateDBQueue.get(block=False)
if id2:
params = ['true',id2]
sqlupdate = "UPDATE tblURL SET processed=? WHERE id=?"
k.execute3(sqlupdate,params)
except Queue.Empty:
print "thread exiting, id: " + str(thread_id) + "**update**"
sys.exit()
# fill the queue with work and block until we are done filling the queue
producer_thread = Thread(target=putURL)
producer_thread.start()
producer_thread.join()
# we can now start consumers
for i in range(number_of_consumer_threads):
getfromDB = Thread(target=getURL, args=(i,))
getfromDB.start()
thread_list.append(getfromDB)
for i in range(number_of_consumer_threads):
update = Thread(target=updateDB, args=(i,))
update.start()
thread_list2.append(update)
for thread in thread_list:
thread.join()
for thread2 in thread_list2:
thread2.join()