Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Use a monotonic clock

Browse Source
This commit is contained in:
Kovid Goyal 2020-12-27 19:26:10 +05:30
parent bec6c7c0cd
commit fe1886393b
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 19 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
src/calibre/web/fetch/simple.py
View File

@ -236,7 +236,7 @@ class RecursiveFetcher(object):
def fetch_url(self, url): def fetch_url(self, url):
data = None data = None
self.log.debug('Fetching', url) self.log.debug('Fetching', url)
st = time.time() st = time.monotonic()
# Check for a URL pointing to the local filesystem and special case it # Check for a URL pointing to the local filesystem and special case it
# for efficiency and robustness. Bypasses delay checking as it does not # for efficiency and robustness. Bypasses delay checking as it does not
@ -255,10 +255,10 @@ class RecursiveFetcher(object):
data = response(f.read()) data = response(f.read())
data.newurl = 'file:'+url # This is what mechanize does for data.newurl = 'file:'+url # This is what mechanize does for
# local URLs # local URLs
self.log.debug('Fetched %s in %.1f seconds' % (url, time.time() - st)) self.log.debug('Fetched %s in %.1f seconds' % (url, time.monotonic() - st))
return data return data
delta = time.time() - self.last_fetch_at delta = time.monotonic() - self.last_fetch_at
if delta < self.delay: if delta < self.delay:
time.sleep(self.delay - delta) time.sleep(self.delay - delta)
# mechanize does not handle quoting automatically # mechanize does not handle quoting automatically
@ -292,8 +292,8 @@ class RecursiveFetcher(object):
else: else:
raise err raise err
finally: finally:
self.last_fetch_at = time.time() self.last_fetch_at = time.monotonic()
self.log.debug('Fetched %s in %f seconds' % (url, time.time() - st)) self.log.debug('Fetched %s in %f seconds' % (url, time.monotonic() - st))
return data return data
def start_fetch(self, url): def start_fetch(self, url):
@ -341,9 +341,12 @@ class RecursiveFetcher(object):
iurl = tag['href'] iurl = tag['href']
if not urlsplit(iurl).scheme: if not urlsplit(iurl).scheme:
iurl = urljoin(baseurl, iurl, False) iurl = urljoin(baseurl, iurl, False)
found_cached = False
with self.stylemap_lock: with self.stylemap_lock:
if iurl in self.stylemap: if iurl in self.stylemap:
tag['href'] = self.stylemap[iurl] tag['href'] = self.stylemap[iurl]
found_cached = True
if found_cached:
continue continue
try: try:
data = self.fetch_url(iurl) data = self.fetch_url(iurl)
@ -364,9 +367,12 @@ class RecursiveFetcher(object):
iurl = m.group(1) iurl = m.group(1)
if not urlsplit(iurl).scheme: if not urlsplit(iurl).scheme:
iurl = urljoin(baseurl, iurl, False) iurl = urljoin(baseurl, iurl, False)
found_cached = False
with self.stylemap_lock: with self.stylemap_lock:
if iurl in self.stylemap: if iurl in self.stylemap:
ns.replaceWith(src.replace(m.group(1), self.stylemap[iurl])) ns.replaceWith(src.replace(m.group(1), self.stylemap[iurl]))
found_cached = True
if found_cached:
continue continue
try: try:
data = self.fetch_url(iurl) data = self.fetch_url(iurl)
@ -402,9 +408,12 @@ class RecursiveFetcher(object):
iurl = self.image_url_processor(baseurl, iurl) iurl = self.image_url_processor(baseurl, iurl)
if not urlsplit(iurl).scheme: if not urlsplit(iurl).scheme:
iurl = urljoin(baseurl, iurl, False) iurl = urljoin(baseurl, iurl, False)
found_in_cache = False
with self.imagemap_lock: with self.imagemap_lock:
if iurl in self.imagemap: if iurl in self.imagemap:
tag['src'] = self.imagemap[iurl] tag['src'] = self.imagemap[iurl]
found_in_cache = True
if found_in_cache:
continue continue
try: try:
data = self.fetch_url(iurl) data = self.fetch_url(iurl)
@ -529,9 +538,9 @@ class RecursiveFetcher(object):
else: else:
dsrc = xml_to_unicode(dsrc, self.verbose)[0] dsrc = xml_to_unicode(dsrc, self.verbose)[0]
st = time.time() st = time.monotonic()
soup = self.get_soup(dsrc, url=iurl) soup = self.get_soup(dsrc, url=iurl)
self.log.debug('Parsed %s in %.1f seconds' % (iurl, time.time() - st)) self.log.debug('Parsed %s in %.1f seconds' % (iurl, time.monotonic() - st))
base = soup.find('base', href=True) base = soup.find('base', href=True)
if base is not None: if base is not None: