2012-06-20 20:41:04 +00:00
|
|
|
# -*- coding: iso-8859-1 -*-
|
|
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
|
|
|
# Copyright (C) 2012 Bastian Kleineidam
|
2012-06-20 19:58:13 +00:00
|
|
|
import tempfile
|
|
|
|
import shutil
|
2012-11-13 18:12:28 +00:00
|
|
|
import re
|
2012-10-11 12:55:54 +00:00
|
|
|
from itertools import islice
|
2012-06-20 19:58:13 +00:00
|
|
|
from unittest import TestCase
|
|
|
|
from dosagelib import scraper
|
|
|
|
|
|
|
|
|
|
|
|
class _ComicTester(TestCase):
|
|
|
|
"""Basic comic test class."""
|
|
|
|
scraperclass=None
|
|
|
|
|
2012-10-11 12:40:54 +00:00
|
|
|
def setUp(self):
|
|
|
|
self.name = self.scraperclass.get_name()
|
2012-10-11 18:19:10 +00:00
|
|
|
self.url = self.scraperclass.starter()
|
2012-10-11 12:40:54 +00:00
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
def test_comic(self):
|
|
|
|
# Test a scraper. It must be able to traverse backward for
|
2012-11-13 18:12:28 +00:00
|
|
|
# at least 5 strips from the start, and find strip images
|
2012-06-20 19:58:13 +00:00
|
|
|
# on at least 4 pages.
|
2012-10-11 12:40:54 +00:00
|
|
|
scraperobj = self.scraperclass()
|
2012-06-20 19:58:13 +00:00
|
|
|
num = empty = 0
|
2012-10-11 12:55:54 +00:00
|
|
|
for strip in islice(scraperobj.getAllStrips(), 0, 5):
|
2012-10-11 13:17:01 +00:00
|
|
|
images = 0
|
|
|
|
for image in strip.getImages():
|
|
|
|
images += 1
|
2012-10-11 12:40:54 +00:00
|
|
|
self.save(image)
|
2012-11-14 05:21:59 +00:00
|
|
|
if num > 0:
|
2012-11-13 18:12:28 +00:00
|
|
|
# test that the stripUrl regex matches the retrieved strip URL
|
2012-11-14 05:21:59 +00:00
|
|
|
urlmatch = re.escape(self.scraperclass.stripUrl)
|
|
|
|
urlmatch = urlmatch.replace(r"\%s", r".+")
|
|
|
|
urlmatch = "^%s$" % urlmatch
|
|
|
|
ro = re.compile(urlmatch)
|
|
|
|
mo = ro.search(strip.stripUrl)
|
2012-11-20 17:53:53 +00:00
|
|
|
self.check(mo is not None, 'strip URL %r does not match stripUrl pattern %s' % (strip.stripUrl, urlmatch))
|
2012-11-13 18:12:28 +00:00
|
|
|
else:
|
2012-10-11 13:17:01 +00:00
|
|
|
empty += 1
|
2012-06-20 19:58:13 +00:00
|
|
|
num += 1
|
2012-11-20 17:53:53 +00:00
|
|
|
self.check(num >= 4, 'traversal failed after %d strips, check the prevSearch pattern.' % num)
|
|
|
|
self.check(empty <= 1, 'failed to find images on %d pages, check the imageSearch pattern.' % empty)
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2012-10-11 12:40:54 +00:00
|
|
|
def save(self, image):
|
2012-06-20 19:58:13 +00:00
|
|
|
# create a temporary directory
|
|
|
|
tmpdir = tempfile.mkdtemp()
|
|
|
|
try:
|
2012-10-11 12:40:54 +00:00
|
|
|
image.save(tmpdir)
|
2012-11-20 17:53:53 +00:00
|
|
|
except Exception as msg:
|
|
|
|
self.check(False, 'could not save %s to %s: %s' % (image.url, tmpdir, msg))
|
2012-06-20 19:58:13 +00:00
|
|
|
finally:
|
|
|
|
shutil.rmtree(tmpdir)
|
|
|
|
|
2012-10-11 12:40:54 +00:00
|
|
|
def check(self, condition, msg):
|
2012-10-11 18:19:10 +00:00
|
|
|
self.assertTrue(condition, "%s %s %s" % (self.name, self.url, msg))
|
2012-10-11 12:40:54 +00:00
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
def generate_comic_testers():
|
2012-10-11 12:55:54 +00:00
|
|
|
"""For each comic scraper, create a test class."""
|
|
|
|
# Limit number of scraper tests for now
|
2012-10-11 16:18:32 +00:00
|
|
|
max_scrapers = 100
|
2012-10-11 12:55:54 +00:00
|
|
|
for scraperclass in islice(scraper.get_scrapers(), 0, max_scrapers):
|
2012-10-11 12:40:54 +00:00
|
|
|
name = 'Test'+scraperclass.__name__
|
2012-06-20 19:58:13 +00:00
|
|
|
globals()[name] = type(name,
|
|
|
|
(_ComicTester,),
|
2012-10-11 12:40:54 +00:00
|
|
|
dict(scraperclass=scraperclass)
|
2012-06-20 19:58:13 +00:00
|
|
|
)
|
|
|
|
|
|
|
|
generate_comic_testers()
|