Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Refactor the multiple cover download code in to the base class so it can be reused

Browse Source
This commit is contained in:
Kovid Goyal 2013-04-06 11:56:57 +05:30
parent f491ff67cc
commit e7cfdba57c
2 changed files with 35 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
src/calibre/ebooks/metadata/sources/base.py
View File

@ -429,6 +429,40 @@ class Source(Plugin):
mi.tags = list(map(fixcase, mi.tags))
mi.isbn = check_isbn(mi.isbn)
def download_multiple_covers(self, title, authors, urls, get_best_cover, timeout, result_queue, abort, log, prefs_name='max_covers'):
if not urls:
log('No images found for, title: %r and authors: %r'%(title, authors))
return
from threading import Thread
import time
if prefs_name:
urls = urls[:self.prefs[prefs_name]]
if get_best_cover:
urls = urls[:1]
log('Downloading %d covers'%len(urls))
workers = [Thread(target=self.download_image, args=(u, timeout, log, result_queue)) for u in urls]
for w in workers:
w.daemon = True
w.start()
alive = True
start_time = time.time()
while alive and not abort.is_set() and time.time() - start_time < timeout:
alive = False
for w in workers:
if w.is_alive():
alive = True
break
abort.wait(0.1)
def download_image(self, url, timeout, log, result_queue):
try:
ans = self.browser.open_novisit(url, timeout=timeout).read()
result_queue.put((self, ans))
log('Downloaded cover from: %s'%url)
except Exception:
self.log.exception('Failed to download cover from: %r'%url)
# }}}
# Metadata API {{{

31
src/calibre/ebooks/metadata/sources/google_images.py
View File

@ -39,40 +39,11 @@ class GoogleImages(Source):
title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False):
if not title:
return
from threading import Thread
import time
timeout = max(60, timeout) # Needs at least a minute
title = ' '.join(self.get_title_tokens(title))
author = ' '.join(self.get_author_tokens(authors))
urls = self.get_image_urls(title, author, log, abort, timeout)
if not urls:
log('No images found in Google for, title: %r and authors: %r'%(title, author))
return
urls = urls[:self.prefs['max_covers']]
if get_best_cover:
urls = urls[:1]
log('Downloading %d covers'%len(urls))
workers = [Thread(target=self.download_image, args=(url, timeout, log, result_queue)) for url in urls]
for w in workers:
w.daemon = True
w.start()
alive = True
start_time = time.time()
while alive and not abort.is_set() and time.time() - start_time < timeout:
alive = False
for w in workers:
if w.is_alive():
alive = True
break
abort.wait(0.1)
def download_image(self, url, timeout, log, result_queue):
try:
ans = self.browser.open_novisit(url, timeout=timeout).read()
result_queue.put((self, ans))
log('Downloaded cover from: %s'%url)
except Exception:
self.log.exception('Failed to download cover from: %r'%url)
self.download_multiple_covers(title, authors, urls, get_best_cover, timeout, result_queue, abort, log)
def get_image_urls(self, title, author, log, abort, timeout):
from calibre.utils.ipc.simple_worker import fork_job, WorkerError