From 91e1e0aff30c57b4cfb2ab72a42467d9a77763ab Mon Sep 17 00:00:00 2001 From: Pablo Hoffman Date: Sun, 13 Jun 2010 17:31:33 -0300 Subject: [PATCH] fixed bug and updated old code in googledir example project --- examples/googledir/googledir/pipelines.py | 2 +- examples/googledir/googledir/spiders/google_directory.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/googledir/googledir/pipelines.py b/examples/googledir/googledir/pipelines.py index 72294dbeb..4fb10626e 100644 --- a/examples/googledir/googledir/pipelines.py +++ b/examples/googledir/googledir/pipelines.py @@ -7,7 +7,7 @@ class FilterWordsPipeline(object): # put all words in lowercase words_to_filter = ['politics', 'religion'] - def process_item(self, domain, item): + def process_item(self, spider, item): for word in self.words_to_filter: if word in unicode(item['description']).lower(): raise DropItem("Contains forbidden word: %s" % word) diff --git a/examples/googledir/googledir/spiders/google_directory.py b/examples/googledir/googledir/spiders/google_directory.py index 2af52bf1f..b214be283 100644 --- a/examples/googledir/googledir/spiders/google_directory.py +++ b/examples/googledir/googledir/spiders/google_directory.py @@ -7,7 +7,7 @@ from googledir.items import GoogledirItem class GoogleDirectorySpider(CrawlSpider): name = 'directory.google.com' - allow_domains = ['directory.google.com'] + allowed_domains = ['directory.google.com'] start_urls = ['http://directory.google.com/'] rules = (