From 34543c2b2e5bb106a699512f403921ccf96eccf6 Mon Sep 17 00:00:00 2001 From: Rolando Espinoza La fuente Date: Sat, 19 Oct 2013 23:03:20 -0400 Subject: [PATCH] DOCS removed .tld suffix for spider names for the sake of consistency. --- docs/intro/overview.rst | 4 ++-- docs/topics/settings.rst | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/intro/overview.rst b/docs/intro/overview.rst index eed4bdac4..7ec2eb07d 100644 --- a/docs/intro/overview.rst +++ b/docs/intro/overview.rst @@ -137,7 +137,7 @@ Finally, here's the spider code:: class MininovaSpider(CrawlSpider): - name = 'mininova.org' + name = 'mininova' allowed_domains = ['mininova.org'] start_urls = ['http://www.mininova.org/today'] rules = [Rule(SgmlLinkExtractor(allow=['/tor/\d+']), 'parse_torrent')] @@ -161,7 +161,7 @@ Run the spider to extract the data Finally, we'll run the spider to crawl the site an output file ``scraped_data.json`` with the scraped data in JSON format:: - scrapy crawl mininova.org -o scraped_data.json -t json + scrapy crawl mininova -o scraped_data.json -t json This uses :ref:`feed exports ` to generate the JSON file. You can easily change the export format (XML or CSV, for example) or the diff --git a/docs/topics/settings.rst b/docs/topics/settings.rst index dce63ff30..5c1faa3a1 100644 --- a/docs/topics/settings.rst +++ b/docs/topics/settings.rst @@ -56,7 +56,7 @@ Settings attribute. Example:: - scrapy crawl domain.com -s LOG_FILE=scrapy.log + scrapy crawl myspider -s LOG_FILE=scrapy.log 2. Project settings module --------------------------