X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=trunk%2Fpycurl%2Fexamples%2Fretriever.py;fp=trunk%2Fpycurl%2Fexamples%2Fretriever.py;h=2c91d07f4ec18ba0dbf3bbbe0192414fe68f7168;hb=5a4c1b1278ffa01e630fde47f7c54888ed20a576;hp=0000000000000000000000000000000000000000;hpb=cee5ab52df1c9f38b6eaff2dd354cb22f59028c7;p=plcapi.git

diff --git a/trunk/pycurl/examples/retriever.py b/trunk/pycurl/examples/retriever.py
new file mode 100644
index 0000000..2c91d07
--- /dev/null
+++ b/trunk/pycurl/examples/retriever.py
@@ -0,0 +1,99 @@
+#! /usr/bin/env python
+# -*- coding: iso-8859-1 -*-
+# vi:ts=4:et
+# $Id$
+
+#
+# Usage: python retriever.py <file with URLs to fetch> [<# of
+#          concurrent connections>]
+#
+
+import sys, threading, Queue
+import pycurl
+
+# We should ignore SIGPIPE when using pycurl.NOSIGNAL - see
+# the libcurl tutorial for more info.
+try:
+    import signal
+    from signal import SIGPIPE, SIG_IGN
+    signal.signal(signal.SIGPIPE, signal.SIG_IGN)
+except ImportError:
+    pass
+
+
+# Get args
+num_conn = 10
+try:
+    if sys.argv[1] == "-":
+        urls = sys.stdin.readlines()
+    else:
+        urls = open(sys.argv[1]).readlines()
+    if len(sys.argv) >= 3:
+        num_conn = int(sys.argv[2])
+except:
+    print "Usage: %s <file with URLs to fetch> [<# of concurrent connections>]" % sys.argv[0]
+    raise SystemExit
+
+
+# Make a queue with (url, filename) tuples
+queue = Queue.Queue()
+for url in urls:
+    url = url.strip()
+    if not url or url[0] == "#":
+        continue
+    filename = "doc_%03d.dat" % (len(queue.queue) + 1)
+    queue.put((url, filename))
+
+
+# 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
+            fp = open(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()