why the scrapy-plugins/scrapy-jsonrpc can't get the spider's stats - scrapy

Question

I just want monitor my running spider's stats.I get the latest scrapy-plugins/scrapy-jsonrpc and set the spider as follows:
EXTENSIONS = {
'scrapy_jsonrpc.webservice.WebService': 500,
}
JSONRPC_ENABLED = True
JSONRPC_PORT = [60853]
but when I browse the http://localhost:60853/ , it just return
{"resources": ["crawler"]}
and I just can get the running spiders name without the stats.
anyone who can told me, which place I set wrong, thanks!

Answer 1

http://localhost:60853/ returns the resources available, /crawler being the only top-level one.
If you want to get stats for a spider, you'll need to query the /crawler/stats endpoint and call get_stats().
Here's an example using python-jsonrpc: (here I configured the webservice to listen on localhost and port 6024)
>>> import pyjsonrpc
>>> http_client = pyjsonrpc.HttpClient('http://localhost:6024/crawler/stats')
>>> http_client.call('get_stats', 'httpbin')
{u'log_count/DEBUG': 4, u'scheduler/dequeued': 4, u'log_count/INFO': 9, u'downloader/response_count': 2, u'downloader/response_status_count/200': 2, u'log_count/WARNING': 1, u'scheduler/enqueued/memory': 4, u'downloader/response_bytes': 639, u'start_time': u'2016-09-28 08:49:57', u'scheduler/dequeued/memory': 4, u'scheduler/enqueued': 4, u'downloader/request_bytes': 862, u'response_received_count': 2, u'downloader/request_method_count/GET': 4, u'downloader/request_count': 4}
>>> http_client.call('get_stats')
{u'log_count/DEBUG': 4, u'scheduler/dequeued': 4, u'log_count/INFO': 9, u'downloader/response_count': 2, u'downloader/response_status_count/200': 2, u'log_count/WARNING': 1, u'scheduler/enqueued/memory': 4, u'downloader/response_bytes': 639, u'start_time': u'2016-09-28 08:49:57', u'scheduler/dequeued/memory': 4, u'scheduler/enqueued': 4, u'downloader/request_bytes': 862, u'response_received_count': 2, u'downloader/request_method_count/GET': 4, u'downloader/request_count': 4}
>>> from pprint import pprint
>>> pprint(http_client.call('get_stats'))
{u'downloader/request_bytes': 862,
u'downloader/request_count': 4,
u'downloader/request_method_count/GET': 4,
u'downloader/response_bytes': 639,
u'downloader/response_count': 2,
u'downloader/response_status_count/200': 2,
u'log_count/DEBUG': 4,
u'log_count/INFO': 9,
u'log_count/WARNING': 1,
u'response_received_count': 2,
u'scheduler/dequeued': 4,
u'scheduler/dequeued/memory': 4,
u'scheduler/enqueued': 4,
u'scheduler/enqueued/memory': 4,
u'start_time': u'2016-09-28 08:49:57'}
>>>
You can also use jsonrpc_client_call from scrapy_jsonrpc.jsonrpc.
>>> from scrapy_jsonrpc.jsonrpc import jsonrpc_client_call
>>> jsonrpc_client_call('http://localhost:6024/crawler/stats', 'get_stats', 'httpbin')
{u'log_count/DEBUG': 5, u'scheduler/dequeued': 4, u'log_count/INFO': 11, u'downloader/response_count': 3, u'downloader/response_status_count/200': 3, u'log_count/WARNING': 1, u'scheduler/enqueued/memory': 4, u'downloader/response_bytes': 870, u'start_time': u'2016-09-28 09:01:47', u'scheduler/dequeued/memory': 4, u'scheduler/enqueued': 4, u'downloader/request_bytes': 862, u'response_received_count': 3, u'downloader/request_method_count/GET': 4, u'downloader/request_count': 4}
This is what you get "on the wire" for a request made with a modified example-client.py (see code a bit below, the example in https://github.com/scrapy-plugins/scrapy-jsonrpc is outdated as I write these lines):
POST /crawler/stats HTTP/1.1
Accept-Encoding: identity
Content-Length: 73
Host: localhost:6024
Content-Type: application/x-www-form-urlencoded
Connection: close
User-Agent: Python-urllib/2.7
{"params": ["httpbin"], "jsonrpc": "2.0", "method": "get_stats", "id": 1}
And the response
HTTP/1.1 200 OK
Content-Length: 504
Access-Control-Allow-Headers: X-Requested-With
Server: TwistedWeb/16.4.1
Connection: close
Date: Tue, 27 Sep 2016 11:21:43 GMT
Access-Control-Allow-Origin: *
Access-Control-Allow-Methods: GET, POST, PATCH, PUT, DELETE
Content-Type: application/json
{"jsonrpc": "2.0", "result": {"log_count/DEBUG": 5, "scheduler/dequeued": 4, "log_count/INFO": 11, "downloader/response_count": 3, "downloader/response_status_count/200": 3, "log_count/WARNING": 3, "scheduler/enqueued/memory": 4, "downloader/response_bytes": 870, "start_time": "2016-09-27 11:16:25", "scheduler/dequeued/memory": 4, "scheduler/enqueued": 4, "downloader/request_bytes": 862, "response_received_count": 3, "downloader/request_method_count/GET": 4, "downloader/request_count": 4}, "id": 1}
Here's the modified client to query /crawler/stats, which I called with ./example-client.py -H localhost -P 6024 get-spider-stats httpbin (for a running "httpbin" spider, JSONRPC_PORT being 6024 for me)
#!/usr/bin/env python
"""
Example script to control a Scrapy server using its JSON-RPC web service.
It only provides a reduced functionality as its main purpose is to illustrate
how to write a web service client. Feel free to improve or write you own.
Also, keep in mind that the JSON-RPC API is not stable. The recommended way for
controlling a Scrapy server is through the execution queue (see the "queue"
command).
"""
from __future__ import print_function
import sys, optparse, urllib, json
from six.moves.urllib.parse import urljoin
from scrapy_jsonrpc.jsonrpc import jsonrpc_client_call, JsonRpcError
def get_commands():
return {
'help': cmd_help,
'stop': cmd_stop,
'list-available': cmd_list_available,
'list-running': cmd_list_running,
'list-resources': cmd_list_resources,
'get-global-stats': cmd_get_global_stats,
'get-spider-stats': cmd_get_spider_stats,
}
def cmd_help(args, opts):
"""help - list available commands"""
print("Available commands:")
for _, func in sorted(get_commands().items()):
print(" ", func.__doc__)
def cmd_stop(args, opts):
"""stop <spider> - stop a running spider"""
jsonrpc_call(opts, 'crawler/engine', 'close_spider', args[0])
def cmd_list_running(args, opts):
"""list-running - list running spiders"""
for x in json_get(opts, 'crawler/engine/open_spiders'):
print(x)
def cmd_list_available(args, opts):
"""list-available - list name of available spiders"""
for x in jsonrpc_call(opts, 'crawler/spiders', 'list'):
print(x)
def cmd_list_resources(args, opts):
"""list-resources - list available web service resources"""
for x in json_get(opts, '')['resources']:
print(x)
def cmd_get_spider_stats(args, opts):
"""get-spider-stats <spider> - get stats of a running spider"""
stats = jsonrpc_call(opts, 'crawler/stats', 'get_stats', args[0])
for name, value in stats.items():
print("%-40s %s" % (name, value))
def cmd_get_global_stats(args, opts):
"""get-global-stats - get global stats"""
stats = jsonrpc_call(opts, 'crawler/stats', 'get_stats')
for name, value in stats.items():
print("%-40s %s" % (name, value))
def get_wsurl(opts, path):
return urljoin("http://%s:%s/"% (opts.host, opts.port), path)
def jsonrpc_call(opts, path, method, *args, **kwargs):
url = get_wsurl(opts, path)
return jsonrpc_client_call(url, method, *args, **kwargs)
def json_get(opts, path):
url = get_wsurl(opts, path)
return json.loads(urllib.urlopen(url).read())
def parse_opts():
usage = "%prog [options] <command> [arg] ..."
description = "Scrapy web service control script. Use '%prog help' " \
"to see the list of available commands."
op = optparse.OptionParser(usage=usage, description=description)
op.add_option("-H", dest="host", default="localhost", \
help="Scrapy host to connect to")
op.add_option("-P", dest="port", type="int", default=6080, \
help="Scrapy port to connect to")
opts, args = op.parse_args()
if not args:
op.print_help()
sys.exit(2)
cmdname, cmdargs, opts = args[0], args[1:], opts
commands = get_commands()
if cmdname not in commands:
sys.stderr.write("Unknown command: %s\n\n" % cmdname)
cmd_help(None, None)
sys.exit(1)
return commands[cmdname], cmdargs, opts
def main():
cmd, args, opts = parse_opts()
try:
cmd(args, opts)
except IndexError:
print(cmd.__doc__)
except JsonRpcError as e:
print(str(e))
if e.data:
print("Server Traceback below:")
print(e.data)
if __name__ == '__main__':
main()
In the example command above, I got this:
log_count/DEBUG 5
scheduler/dequeued 4
log_count/INFO 11
downloader/response_count 3
downloader/response_status_count/200 3
log_count/WARNING 3
scheduler/enqueued/memory 4
downloader/response_bytes 870
start_time 2016-09-27 11:16:25
scheduler/dequeued/memory 4
scheduler/enqueued 4
downloader/request_bytes 862
response_received_count 3
downloader/request_method_count/GET 4
downloader/request_count 4