def test_for_list_of_all_valid_links(self):
all_links = []
for c in hundredgreatest.get_all_compiled_links(
hundredgreatest.raw_compiled_soups(
hundredgreatest.setup(hundredgreatest.BASEURL))):
for l in c:
all_links.append(l)
self.assertEqual(hundredgreatest.put_all_compiled_links_in_list(), all_links)
def test_compiled_soups(self):
compiled_soups = set()
valid_urls = {"{0}{1}{2}".format(BEST_NOVELS, "?page=", l) for l in
hundredgreatest.get_follow_on_link_numbers(self.soup)}
# valid_urls = {BEST_NOVELS, BEST_NOVELS + "?page=2", BEST_NOVELS + "?page=3", BEST_NOVELS + "?page=4"}
valid_urls.add(BEST_NOVELS)
for u in valid_urls:
r = urllib.request.urlopen(u)
html = r.read()
soup = BeautifulSoup(html)
compiled_soups.add(soup)
self.assertEqual(hundredgreatest.raw_compiled_soups(self.soup), compiled_soups)
def test_get_all_novel_titles(self):
all_links = []
for c in hundredgreatest.get_all_compiled_links(
hundredgreatest.raw_compiled_soups(
hundredgreatest.setup(hundredgreatest.BASEURL))):
for l in c:
all_links.append(l)
regex_for_all_links = re.compile(r"<a.*\"(.*)\">(.*)</a>")
regex_for_novel_titles = re.compile(r"<a.*>(The 100 best novels: No.*)</a>")
novel_only_titles = []
list_of_link_texts = []
list_of_link_link_urls = []
for link in all_links:
r = re.search(regex_for_all_links, link)
rn = re.search(regex_for_novel_titles, link)
if r:
list_of_link_texts.append(r.group(2))
list_of_link_link_urls.append(r.group(1))
if rn:
novel_only_titles.append(rn.group(1))
self.assertEqual(hundredgreatest.get_all_novel_titles(), novel_only_titles)
def test_get_links_in_all_compiled_raw_soups(self):
compiled_soups = hundredgreatest.raw_compiled_soups(self.soup)
all_links = []
for s in compiled_soups:
all_links.append(hundredgreatest.all_links_as_strings(s))
self.assertEqual(hundredgreatest.get_all_compiled_links(compiled_soups), all_links)