1
0
mirror of https://github.com/moparisthebest/wget synced 2024-07-03 16:38:41 -04:00
wget/testenv/Test--spider-r.py
Zihang Chen 8b83306d54 Refactor the Python based test suite
This is a squashed commit of the following from parallel-wget:
ecd6977 Refactor mainly the test cases classes
d26c8eb Create package test for test case classes
507383d Move server classes to package server.protocol
195393b Create package conf where rules and hooks are put
42e482a Create package exc and move TestFailed to exc
82f44f3 Fix a typo in Test-Proto.py
31e5f33 From WgetTest.py move WgetFile to misc
422171d Create package misc, move ColourTerm.py to misc
2014-07-24 16:51:58 +05:30

107 lines
2.4 KiB
Python
Executable File

#!/usr/bin/env python3
from sys import exit
from test.http_test import HTTPTest
from misc.wget_file import WgetFile
"""
This test executed Wget in Spider mode with recursive retrieval.
"""
TEST_NAME = "Recursive Spider"
############# File Definitions ###############################################
mainpage = """
<html>
<head>
<title>Main Page</title>
</head>
<body>
<p>
Some text and a link to a <a href="http://127.0.0.1:{{port}}/secondpage.html">second page</a>.
Also, a <a href="http://127.0.0.1:{{port}}/nonexistent">broken link</a>.
</p>
</body>
</html>
"""
secondpage = """
<html>
<head>
<title>Second Page</title>
</head>
<body>
<p>
Some text and a link to a <a href="http://127.0.0.1:{{port}}/thirdpage.html">third page</a>.
Also, a <a href="http://127.0.0.1:{{port}}/nonexistent">broken link</a>.
</p>
</body>
</html>
"""
thirdpage = """
<html>
<head>
<title>Third Page</title>
</head>
<body>
<p>
Some text and a link to a <a href="http://127.0.0.1:{{port}}/dummy.txt">text file</a>.
Also, another <a href="http://127.0.0.1:{{port}}/againnonexistent">broken link</a>.
</p>
</body>
</html>
"""
dummyfile = "Don't care."
index_html = WgetFile ("index.html", mainpage)
secondpage_html = WgetFile ("secondpage.html", secondpage)
thirdpage_html = WgetFile ("thirdpage.html", thirdpage)
dummy_txt = WgetFile ("dummy.txt", dummyfile)
Request_List = [
[
"HEAD /",
"GET /",
"GET /robots.txt",
"HEAD /secondpage.html",
"GET /secondpage.html",
"HEAD /nonexistent",
"HEAD /thirdpage.html",
"GET /thirdpage.html",
"HEAD /dummy.txt",
"HEAD /againnonexistent"
]
]
WGET_OPTIONS = "-d --spider -r"
WGET_URLS = [[""]]
Files = [[index_html, secondpage_html, thirdpage_html, dummy_txt]]
ExpectedReturnCode = 8
ExpectedDownloadedFiles = []
################ Pre and Post Test Hooks #####################################
pre_test = {
"ServerFiles" : Files
}
test_options = {
"WgetCommands" : WGET_OPTIONS,
"Urls" : WGET_URLS
}
post_test = {
"ExpectedFiles" : ExpectedDownloadedFiles,
"ExpectedRetcode" : ExpectedReturnCode,
"FilesCrawled" : Request_List
}
err = HTTPTest (
name=TEST_NAME,
pre_hook=pre_test,
test_params=test_options,
post_hook=post_test
).begin ()
exit (err)