Git-Mirrors/brozzler
1
0
Fork 0
mirror of https://github.com/internetarchive/brozzler.git synced 2025-02-24 08:39:59 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity

logging.warn is deprecated and replaced by logging.warning

Browse Source 
We replace it everywhere in the code base.
This commit is contained in:
Vangelis Banos 2019-05-14 12:10:59 +00:00
parent ee8ef23f0c
commit a2ac3a0374
8 changed files with 20 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
brozzler/__init__.py
View File

@ -159,7 +159,7 @@ class ThreadExceptionGate:
def queue_exception(self, e): def queue_exception(self, e):
with self.lock: with self.lock:
if self.pending_exception: if self.pending_exception:
self.logger.warn( self.logger.warning(
'%r already pending for thread %r, discarding %r', '%r already pending for thread %r, discarding %r',
self.pending_exception, self.thread, e) self.pending_exception, self.thread, e)
else: else:

8
brozzler/chrome.py
View File

@ -223,7 +223,7 @@ class Chrome:
raise raise
except Exception as e: except Exception as e:
if time.time() - self._last_warning > 30: if time.time() - self._last_warning > 30:
self.logger.warn( self.logger.warning(
'problem with %s (will keep trying until timeout ' 'problem with %s (will keep trying until timeout '
'of %d seconds): %s', json_url, timeout_sec, e) 'of %d seconds): %s', json_url, timeout_sec, e)
self._last_warning = time.time() self._last_warning = time.time()
@ -294,7 +294,7 @@ class Chrome:
'chrome pid %s exited normally', 'chrome pid %s exited normally',
self.chrome_process.pid) self.chrome_process.pid)
else: else:
self.logger.warn( self.logger.warning(
'chrome pid %s exited with nonzero status %s', 'chrome pid %s exited with nonzero status %s',
self.chrome_process.pid, status) self.chrome_process.pid, status)
@ -305,13 +305,13 @@ class Chrome:
return return
time.sleep(0.5) time.sleep(0.5)
self.logger.warn( self.logger.warning(
'chrome pid %s still alive %.1f seconds after sending ' 'chrome pid %s still alive %.1f seconds after sending '
'SIGTERM, sending SIGKILL', self.chrome_process.pid, 'SIGTERM, sending SIGKILL', self.chrome_process.pid,
time.time() - t0) time.time() - t0)
os.killpg(self.chrome_process.pid, signal.SIGKILL) os.killpg(self.chrome_process.pid, signal.SIGKILL)
status = self.chrome_process.wait() status = self.chrome_process.wait()
self.logger.warn( self.logger.warning(
'chrome pid %s reaped (status=%s) after killing with ' 'chrome pid %s reaped (status=%s) after killing with '
'SIGKILL', self.chrome_process.pid, status) 'SIGKILL', self.chrome_process.pid, status)

6
brozzler/cli.py
View File

@ -627,7 +627,7 @@ def brozzler_purge(argv=None):
sys.exit(1) sys.exit(1)
if job.status == 'ACTIVE': if job.status == 'ACTIVE':
if args.force: if args.force:
logging.warn( logging.warning(
'job %s has status ACTIVE, purging anyway because ' 'job %s has status ACTIVE, purging anyway because '
'--force was supplied', job_id) '--force was supplied', job_id)
else: else:
@ -644,7 +644,7 @@ def brozzler_purge(argv=None):
sys.exit(1) sys.exit(1)
if site.status == 'ACTIVE': if site.status == 'ACTIVE':
if args.force: if args.force:
logging.warn( logging.warning(
'site %s has status ACTIVE, purging anyway because ' 'site %s has status ACTIVE, purging anyway because '
'--force was supplied', site_id) '--force was supplied', site_id)
else: else:
@ -712,7 +712,7 @@ def brozzler_list_captures(argv=None):
if args.url_or_sha1[:5] == 'sha1:': if args.url_or_sha1[:5] == 'sha1:':
if args.prefix: if args.prefix:
logging.warn( logging.warning(
'ignoring supplied --prefix option which does not apply ' 'ignoring supplied --prefix option which does not apply '
'to lookup by sha1') 'to lookup by sha1')
# assumes it's already base32 (XXX could detect if hex and convert) # assumes it's already base32 (XXX could detect if hex and convert)

2
brozzler/easy.py
View File

@ -260,7 +260,7 @@ class BrozzlerEasyController:
state_strs.append(str(th)) state_strs.append(str(th))
stack = traceback.format_stack(sys._current_frames()[th.ident]) stack = traceback.format_stack(sys._current_frames()[th.ident])
state_strs.append(''.join(stack)) state_strs.append(''.join(stack))
logging.warn('dumping state (caught signal {})\n{}'.format( logging.warning('dumping state (caught signal {})\n{}'.format(
signum, '\n'.join(state_strs))) signum, '\n'.join(state_strs)))
def main(argv=None): def main(argv=None):

8
brozzler/frontier.py
View File

@ -138,7 +138,7 @@ class RethinkDbFrontier:
sites = [] sites = []
for i in range(result["replaced"]): for i in range(result["replaced"]):
if result["changes"][i]["old_val"]["claimed"]: if result["changes"][i]["old_val"]["claimed"]:
self.logger.warn( self.logger.warning(
"re-claimed site that was still marked 'claimed' " "re-claimed site that was still marked 'claimed' "
"because it was last claimed a long time ago " "because it was last claimed a long time ago "
"at %s, and presumably some error stopped it from " "at %s, and presumably some error stopped it from "
@ -225,7 +225,7 @@ class RethinkDbFrontier:
if not job: if not job:
return False return False
if job.status.startswith("FINISH"): if job.status.startswith("FINISH"):
self.logger.warn("%s is already %s", job, job.status) self.logger.warning("%s is already %s", job, job.status)
return True return True
results = self.rr.table("sites").get_all(job_id, index="job_id").run() results = self.rr.table("sites").get_all(job_id, index="job_id").run()
@ -415,7 +415,7 @@ class RethinkDbFrontier:
assert isinstance(e, brozzler.ReachedLimit) assert isinstance(e, brozzler.ReachedLimit)
if (site.reached_limit if (site.reached_limit
and site.reached_limit != e.warcprox_meta["reached-limit"]): and site.reached_limit != e.warcprox_meta["reached-limit"]):
self.logger.warn( self.logger.warning(
"reached limit %s but site had already reached limit %s", "reached limit %s but site had already reached limit %s",
e.warcprox_meta["reached-limit"], self.reached_limit) e.warcprox_meta["reached-limit"], self.reached_limit)
else: else:
@ -434,7 +434,7 @@ class RethinkDbFrontier:
index="priority_by_site").filter({"hops_from_seed":0}).run() index="priority_by_site").filter({"hops_from_seed":0}).run()
pages = list(results) pages = list(results)
if len(pages) > 1: if len(pages) > 1:
self.logger.warn( self.logger.warning(
"more than one seed page for site_id %s ?", site_id) "more than one seed page for site_id %s ?", site_id)
if len(pages) < 1: if len(pages) < 1:
return None return None

2
brozzler/robots.py
View File

@ -106,7 +106,7 @@ def is_permitted_by_robots(site, url, proxy=None):
# reppy has wrapped an exception that we want to bubble up # reppy has wrapped an exception that we want to bubble up
raise brozzler.ProxyError(e) raise brozzler.ProxyError(e)
else: else:
logging.warn( logging.warning(
"returning true (permitted) after problem fetching " "returning true (permitted) after problem fetching "
"robots.txt for %r: %r", url, e) "robots.txt for %r: %r", url, e)
return True return True

8
brozzler/worker.py
View File

@ -147,13 +147,13 @@ class BrozzlerWorker:
try: try:
with urllib.request.urlopen(request, timeout=600) as response: with urllib.request.urlopen(request, timeout=600) as response:
if response.getcode() != 204: if response.getcode() != 204:
self.logger.warn( self.logger.warning(
'got "%s %s" response on warcprox ' 'got "%s %s" response on warcprox '
'WARCPROX_WRITE_RECORD request (expected 204)', 'WARCPROX_WRITE_RECORD request (expected 204)',
response.getcode(), response.reason) response.getcode(), response.reason)
return request, response return request, response
except urllib.error.HTTPError as e: except urllib.error.HTTPError as e:
self.logger.warn( self.logger.warning(
'got "%s %s" response on warcprox ' 'got "%s %s" response on warcprox '
'WARCPROX_WRITE_RECORD request (expected 204)', 'WARCPROX_WRITE_RECORD request (expected 204)',
e.getcode(), e.info()) e.getcode(), e.info())
@ -370,7 +370,7 @@ class BrozzlerWorker:
if (page.needs_robots_check and if (page.needs_robots_check and
not brozzler.is_permitted_by_robots( not brozzler.is_permitted_by_robots(
site, page.url, self._proxy_for(site))): site, page.url, self._proxy_for(site))):
logging.warn("page %s is blocked by robots.txt", page.url) logging.warning("page %s is blocked by robots.txt", page.url)
page.blocked_by_robots = True page.blocked_by_robots = True
self._frontier.completed_page(site, page) self._frontier.completed_page(site, page)
else: else:
@ -544,7 +544,7 @@ class BrozzlerWorker:
def start(self): def start(self):
with self._start_stop_lock: with self._start_stop_lock:
if self._thread: if self._thread:
self.logger.warn( self.logger.warning(
'ignoring start request because self._thread is ' 'ignoring start request because self._thread is '
'not None') 'not None')
return return

4
brozzler/ydl.py
View File

@ -48,7 +48,7 @@ _orig_webpage_read_content = youtube_dl.extractor.generic.GenericIE._webpage_rea
def _webpage_read_content(self, *args, **kwargs): def _webpage_read_content(self, *args, **kwargs):
content = _orig_webpage_read_content(self, *args, **kwargs) content = _orig_webpage_read_content(self, *args, **kwargs)
if len(content) > 20000000: if len(content) > 20000000:
logging.warn( logging.warning(
'bypassing youtube-dl extraction because content is ' 'bypassing youtube-dl extraction because content is '
'too large (%s characters)', len(content)) 'too large (%s characters)', len(content))
return '' return ''
@ -185,7 +185,7 @@ def _build_youtube_dl(worker, destdir, site):
mimetype = magic.from_file(ctx['filename'], mime=True) mimetype = magic.from_file(ctx['filename'], mime=True)
except ImportError as e: except ImportError as e:
mimetype = 'video/%s' % info_dict['ext'] mimetype = 'video/%s' % info_dict['ext']
self.logger.warn( self.logger.warning(
'guessing mimetype %s because %r', mimetype, e) 'guessing mimetype %s because %r', mimetype, e)
url = 'youtube-dl:%05d:%s' % ( url = 'youtube-dl:%05d:%s' % (