From 6d6cff33ca9883ebca27e8cbf4d86e590a437acd Mon Sep 17 00:00:00 2001
From: Pablo Hoffman <pablo@pablohoffman.com>
Date: Sat, 27 Aug 2011 01:23:36 -0300
Subject: [PATCH] added scrapyd system test script to extras/test-scrapyd.sh

---
 extras/test-scrapyd.sh | 99 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)
 create mode 100755 extras/test-scrapyd.sh

diff --git a/extras/test-scrapyd.sh b/extras/test-scrapyd.sh
new file mode 100755
index 000000000..92a1df01b
--- /dev/null
+++ b/extras/test-scrapyd.sh
@@ -0,0 +1,99 @@
+#!/bin/bash
+#
+# This script is a quick system test for Scrapyd that:
+#
+# 1. runs scrapyd
+# 2. creates a new project and deploys it on scrapyd
+# 3. schedules a spider on scrapyd and waits for it to finish
+# 4. check the spider scraped the expected data
+#
+
+set -e
+
+export PATH=$PATH:$(pwd)/bin
+export PYTHONPATH=$PYTHONPATH:$(pwd)
+
+scrapyd_dir=$(mktemp /tmp/test-scrapyd.XXXXXXX -d)
+scrapyd_log=$(mktemp /tmp/test-scrapyd.XXXXXXX.log)
+scrapy_dir=$(mktemp /tmp/test-scrapyd.XXXXXXX -d)
+feed_path=$(mktemp /tmp/test-scrapyd.XXXXXXX.jl)
+
+twistd -ny extras/scrapyd.tac -d $scrapyd_dir -l $scrapyd_log &
+
+cd $scrapy_dir
+scrapy startproject testproj
+cd testproj
+cat > testproj/spiders/insophia.py <<!
+from scrapy.spider import BaseSpider
+from scrapy.selector import HtmlXPathSelector
+from scrapy.http import Request
+from scrapy.item import Item, Field
+
+
+class Section(Item):
+    url = Field()
+    title = Field()
+    size = Field()
+    arg = Field()
+
+
+class InsophiaSpider(BaseSpider):
+    name = 'insophia'
+    start_urls = ['http://insophia.com']
+
+    def __init__(self, *a, **kw):
+        self.arg = kw.pop('arg')
+        super(InsophiaSpider, self).__init__(*a, **kw)
+
+    def parse(self, response):
+        hxs = HtmlXPathSelector(response)
+        for url in hxs.select('//ul[@id="navlist"]/li/a/@href').extract():
+            yield Request(url, callback=self.parse_section)
+
+    def parse_section(self, response):
+        hxs = HtmlXPathSelector(response)
+        title = hxs.select("//h2/text()").extract()[0]
+        yield Section(url=response.url, title=title, size=len(response.body),
+            arg=self.arg)
+!
+
+cat > scrapy.cfg <<!
+[settings]
+default = testproj.settings
+
+[deploy]
+url = http://localhost:6800/
+project = testproj
+!
+
+scrapy deploy
+
+curl -s http://localhost:6800/schedule.json -d project=testproj -d spider=insophia -d setting=FEED_URI=$feed_path -d arg=SOME_ARGUMENT
+
+echo "waiting for spider to finish..."
+until grep -q "Process finished" $scrapyd_log; do
+    sleep 1
+done
+
+kill %1
+wait %1
+
+numitems="$(cat $feed_path | wc -l)"
+if [ "$numitems" != "8" ]; then
+    echo "error: wrong number of items scraped: $numitems"
+    exit 1
+fi
+
+if ! grep -q "About Us" $feed_path; then
+    echo "error: About Us page not scraped"
+    exit 1
+fi
+
+if ! grep -q "SOME_ARGUMENT" $feed_path; then
+    echo "error: spider argument not found in scraped items"
+    exit 1
+fi
+
+rm -rf /tmp/test-scrapyd.*
+
+echo "All tests OK"