CODEWITHSUNDEEP
pythonpython-2.7pycurl
JohnDotOwl
JohnDotOwl

Reputation: 3755

Python Curl - Illegal Characters Found in URL

error: (3, 'Illegal characters found in URL')

My url has got special characters like [AVC_(1)_(P1)_0] i cant get this to work, i tried encoding but that would give me "Could not resolve host: https%3A"

Please advice 

import sys
import Queue
import threading
import pycurl
import os
import urllib
from StringIO import StringIO
num_conn = 1
# Make a queue with (url, filename) tuples
queue = Queue.Queue()
with open('list.txt') as f:
   for line in f:
       print line
       queue.put((line, 'test.mp4'))
       if 'str' in line:
          break

# Check args
assert queue.queue, "no URLs given"
num_urls = len(queue.queue)
num_conn = min(num_conn, num_urls)
assert 1 <= num_conn <= 10000, "invalid number of concurrent connections"
print "PycURL %s (compiled against 0x%x)" % (pycurl.version, pycurl.COMPILE_LIBCURL_VERSION_NUM)
print "----- Getting", num_urls, "URLs using", num_conn, "connections -----"


class WorkerThread(threading.Thread):
    def __init__(self, queue):
        threading.Thread.__init__(self)
        self.queue = queue

    def run(self):
        while 1:
            try:
                url, filename = self.queue.get_nowait()
            except Queue.Empty:
                raise SystemExit
            #dirname = os.path.dirname(filename)
            #fp = open(dirname, "wb")\
            #url = urllib.quote(url.encode('utf-8'))
            fp = open(os.getcwd()+'/'+filename, "wb")
            curl = pycurl.Curl()
            curl.setopt(pycurl.URL, url)
            curl.setopt(pycurl.FOLLOWLOCATION, 1)
            curl.setopt(pycurl.MAXREDIRS, 5)
            curl.setopt(pycurl.CONNECTTIMEOUT, 30)
            curl.setopt(pycurl.TIMEOUT, 300)
            curl.setopt(pycurl.NOSIGNAL, 1)
            curl.setopt(pycurl.WRITEDATA, fp)
            try:
                curl.perform()
            except:
                import traceback
                traceback.print_exc(file=sys.stderr)
                sys.stderr.flush()
            curl.close()
            fp.close()
            sys.stdout.write(".")
            sys.stdout.flush()


# Start a bunch of threads
threads = []
for dummy in range(num_conn):
    t = WorkerThread(queue)
    t.start()
    threads.append(t)


# Wait for all threads to finish
for thread in threads:
    thread.join()

Upvotes: 0

Views: 448

Answers (1)

hd1
hd1

Reputation: 34667

Why not use requests in lieu of pycurl, which would make your run method:

def run(self):
    while True: 
        try:
            url, filename = self.queue.get_nowait()
        except Queue.Empty:
            raise SystemExit
        with open(os.getcwd()+'/'+filename, "wb") as fp:
            #fp.write(requests.get(url).content)
            fp.write(requests.get(url, headers={'user-agent': 'CodeGuru'}).content

I made a few other, stylistic changes.

Upvotes: 2

Related Questions