Created
February 17, 2012 22:30
-
-
Save DrSkippy/1855814 to your computer and use it in GitHub Desktop.
Python example view of Gnip v2.5 stream output
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import urllib2 | |
import base64 | |
import zlib | |
import threading | |
from threading import Lock | |
from cStringIO import StringIO | |
import json | |
import sys | |
from pprint import pprint | |
# tune these as needed | |
CHUNKSIZE = 1024 | |
MAXBUFFSIZE = 20*CHUNKSIZE | |
NEWLINE = '\n' | |
url = "https://stream.gnip.com:443/accounts/client/publishers/twitter/streams/link/ls.json" | |
UN = 'un' | |
PWD = 'pwd' | |
print_lock = Lock() | |
class procEntry(threading.Thread): | |
def __init__(self, buf): | |
self.bufList = [x.strip() for x in buf.split(NEWLINE) if x.strip() <> ''] | |
threading.Thread.__init__(self) | |
def run(self): | |
try: | |
self.output(self.bufList) | |
except Exception, e: # v hard to debug, catches everything! | |
sys.stderr.write("thread failed: (%s)\n"%e) | |
def output(self, bufList): | |
for rec in bufList: | |
jrec = json.loads(rec.strip()) | |
with print_lock: | |
pprint(jrec) | |
print "="*40 | |
def get(): | |
headers = { | |
'Accept': 'application/json', | |
'Connection': 'keep-alive', | |
'Accept-Encoding' : 'gzip', | |
'Authorization' : 'Basic %s' % base64.encodestring('%s:%s' % (UN, PWD)) | |
} | |
req = urllib2.Request(url, headers=headers) | |
response = urllib2.urlopen(req) | |
d = zlib.decompressobj(16+zlib.MAX_WBITS) | |
ldata = StringIO() | |
bufSize = 0 | |
while True: | |
tmpString = d.decompress(response.read(CHUNKSIZE)) | |
bufSize += len(tmpString) | |
ldata.write(tmpString) | |
if tmpString.endswith(NEWLINE) and bufSize > MAXBUFFSIZE: | |
procEntry(ldata.getvalue()).start() | |
ldata = StringIO() | |
bufSize = 0 | |
if __name__ == "__main__": | |
get() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment