cache imdb urls in parallel
This commit is contained in:
parent
cc1bad76cd
commit
388f33ebb6
1 changed files with 5 additions and 0 deletions
|
@ -1,6 +1,7 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
# vi:si:et:sw=4:sts=4:ts=4
|
||||
import re
|
||||
from multiprocessing.pool import ThreadPool
|
||||
|
||||
from six import string_types
|
||||
|
||||
|
@ -28,6 +29,7 @@ def cleanup(key, data, data_type):
|
|||
class SiteParser(dict):
|
||||
baseUrl = ''
|
||||
regex = {}
|
||||
pool = ThreadPool(8)
|
||||
|
||||
def get_url(self, page):
|
||||
return "%s%s" % (self.baseUrl, page)
|
||||
|
@ -39,6 +41,9 @@ class SiteParser(dict):
|
|||
|
||||
def __init__(self, timeout=-1):
|
||||
self._cache = {}
|
||||
urls = list(set(self.get_url(self.regex[key]['page']) for key in self.regex))
|
||||
self.pool.map(self.get_url, urls)
|
||||
|
||||
for key in self.regex:
|
||||
url = self.get_url(self.regex[key]['page'])
|
||||
data = self.read_url(url, timeout)
|
||||
|
|
Loading…
Reference in a new issue