mirror of
https://github.com/internetarchive/warcprox.git
synced 2025-01-18 13:22:09 +01:00
be clear about timezone in timestamps
This commit is contained in:
parent
f082db62cf
commit
dbf868a74d
96
api.rst
96
api.rst
@ -15,72 +15,60 @@ a json blob with a bunch of status info. For example:
|
|||||||
|
|
||||||
$ curl -sS http://localhost:8000/status
|
$ curl -sS http://localhost:8000/status
|
||||||
{
|
{
|
||||||
"rates_5min": {
|
"role": "warcprox",
|
||||||
"warc_bytes_per_sec": 0.0,
|
"version": "2.4b3.dev189",
|
||||||
"urls_per_sec": 0.0,
|
"host": "ayutla.local",
|
||||||
"actual_elapsed": 277.2983281612396
|
"address": "127.0.0.1",
|
||||||
},
|
|
||||||
"version": "2.4b2.dev174",
|
|
||||||
"load": 0.0,
|
|
||||||
"seconds_behind": 0.0,
|
|
||||||
"threads": 100,
|
|
||||||
"warc_bytes_written": 0,
|
|
||||||
"port": 8000,
|
"port": 8000,
|
||||||
|
"pid": 60555,
|
||||||
|
"threads": 100,
|
||||||
|
"active_requests": 1,
|
||||||
|
"unaccepted_requests": 0,
|
||||||
|
"load": 0.0,
|
||||||
|
"queued_urls": 0,
|
||||||
|
"queue_max_size": 500,
|
||||||
|
"urls_processed": 0,
|
||||||
|
"warc_bytes_written": 0,
|
||||||
|
"start_time": "2018-10-30T20:15:19.929861Z",
|
||||||
|
"rates_1min": {
|
||||||
|
"actual_elapsed": 61.76024103164673,
|
||||||
|
"urls_per_sec": 0.0,
|
||||||
|
"warc_bytes_per_sec": 0.0
|
||||||
|
},
|
||||||
|
"rates_5min": {
|
||||||
|
"actual_elapsed": 1.7602601051330566,
|
||||||
|
"urls_per_sec": 0.0,
|
||||||
|
"warc_bytes_per_sec": 0.0
|
||||||
|
},
|
||||||
|
"rates_15min": {
|
||||||
|
"actual_elapsed": 1.7602710723876953,
|
||||||
|
"urls_per_sec": 0.0,
|
||||||
|
"warc_bytes_per_sec": 0.0
|
||||||
|
},
|
||||||
|
"earliest_still_active_fetch_start": "2018-10-30T20:15:21.691467Z",
|
||||||
|
"seconds_behind": 0.001758,
|
||||||
"postfetch_chain": [
|
"postfetch_chain": [
|
||||||
{
|
{
|
||||||
"queued_urls": 0,
|
"processor": "DedupLoader",
|
||||||
"processor": "SkipFacebookCaptchas"
|
"queued_urls": 0
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"queued_urls": 0,
|
"processor": "WarcWriterProcessor",
|
||||||
"processor": "BatchTroughLoader"
|
"queued_urls": 0
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"queued_urls": 0,
|
"processor": "DedupDb",
|
||||||
"processor": "WarcWriterProcessor"
|
"queued_urls": 0
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"queued_urls": 0,
|
"processor": "StatsProcessor",
|
||||||
"processor": "BatchTroughStorer"
|
"queued_urls": 0
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"queued_urls": 0,
|
"processor": "RunningStats",
|
||||||
"processor": "RethinkStatsProcessor"
|
"queued_urls": 0
|
||||||
},
|
|
||||||
{
|
|
||||||
"queued_urls": 0,
|
|
||||||
"processor": "CrawlLogger"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"queued_urls": 0,
|
|
||||||
"processor": "TroughFeed"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"queued_urls": 0,
|
|
||||||
"processor": "RunningStats"
|
|
||||||
}
|
}
|
||||||
],
|
]
|
||||||
"queue_max_size": 500,
|
|
||||||
"role": "warcprox",
|
|
||||||
"queued_urls": 0,
|
|
||||||
"active_requests": 1,
|
|
||||||
"host": "wbgrp-svc405.us.archive.org",
|
|
||||||
"rates_15min": {
|
|
||||||
"warc_bytes_per_sec": 0.0,
|
|
||||||
"urls_per_sec": 0.0,
|
|
||||||
"actual_elapsed": 876.9885368347168
|
|
||||||
},
|
|
||||||
"unaccepted_requests": 0,
|
|
||||||
"urls_processed": 0,
|
|
||||||
"pid": 18841,
|
|
||||||
"address": "127.0.0.1",
|
|
||||||
"rates_1min": {
|
|
||||||
"warc_bytes_per_sec": 0.0,
|
|
||||||
"urls_per_sec": 0.0,
|
|
||||||
"actual_elapsed": 54.92501664161682
|
|
||||||
},
|
|
||||||
"start_time": 1526690353.4060142
|
|
||||||
}
|
|
||||||
|
|
||||||
``WARCPROX_WRITE_RECORD`` http method
|
``WARCPROX_WRITE_RECORD`` http method
|
||||||
=====================================
|
=====================================
|
||||||
|
@ -51,7 +51,7 @@ class Options(_Namespace):
|
|||||||
class Jsonner(json.JSONEncoder):
|
class Jsonner(json.JSONEncoder):
|
||||||
def default(self, o):
|
def default(self, o):
|
||||||
if isinstance(o, datetime.datetime):
|
if isinstance(o, datetime.datetime):
|
||||||
return o.isoformat()
|
return o.isoformat() + 'Z' # we use only utc
|
||||||
elif isinstance(o, bytes):
|
elif isinstance(o, bytes):
|
||||||
return base64.b64encode(o).decode('ascii')
|
return base64.b64encode(o).decode('ascii')
|
||||||
else:
|
else:
|
||||||
|
@ -425,6 +425,7 @@ class SingleThreadedWarcProxy(http_server.HTTPServer, object):
|
|||||||
def __init__(
|
def __init__(
|
||||||
self, stats_db=None, status_callback=None,
|
self, stats_db=None, status_callback=None,
|
||||||
options=warcprox.Options()):
|
options=warcprox.Options()):
|
||||||
|
self.start_time = datetime.datetime.utcnow()
|
||||||
self.status_callback = status_callback
|
self.status_callback = status_callback
|
||||||
self.stats_db = stats_db
|
self.stats_db = stats_db
|
||||||
self.options = options
|
self.options = options
|
||||||
@ -477,7 +478,7 @@ class SingleThreadedWarcProxy(http_server.HTTPServer, object):
|
|||||||
'queue_max_size': self.recorded_url_q.maxsize,
|
'queue_max_size': self.recorded_url_q.maxsize,
|
||||||
'urls_processed': self.running_stats.urls,
|
'urls_processed': self.running_stats.urls,
|
||||||
'warc_bytes_written': self.running_stats.warc_bytes,
|
'warc_bytes_written': self.running_stats.warc_bytes,
|
||||||
'start_time': self.running_stats.first_snap_time,
|
'start_time': self.start_time,
|
||||||
})
|
})
|
||||||
elapsed, urls_per_sec, warc_bytes_per_sec = self.running_stats.current_rates(1)
|
elapsed, urls_per_sec, warc_bytes_per_sec = self.running_stats.current_rates(1)
|
||||||
result['rates_1min'] = {
|
result['rates_1min'] = {
|
||||||
|
Loading…
x
Reference in New Issue
Block a user