def test_find_exclude(self):
""" Determine if excluding links removes the links """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(exclude=[{"class": re.compile("gb1")}])
self.assertEqual(len(actual_list), page['exclude_links'])
actual_list = seek.find(exclude=[{"class": "gb1"}])
self.assertEqual(len(actual_list), page['exclude_links'])
def test_find_reverse_sort(self):
""" Ensure reverse sort sorts before limiting the # of links """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(limit=5, reverse=True)
self.assertEqual(len(actual_list), len(page['limit_reverse_find']))
for i, link in enumerate(actual_list):
self.assertDictSame(link, page['limit_reverse_find'][i])
def test_find_limit(self):
""" Check that the actual array with a limit matches the test data """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(limit=5)
self.assertEqual(len(actual_list), len(page['limit_find']))
for i, link in enumerate(actual_list):
self.assertDictSame(link, page['limit_find'][i])
def test_find_exclude(self):
""" Determine if excluding links removes the links """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(exclude=[{"class": re.compile("gb1")}])
self.assertEqual(len(actual_list), page['exclude_links'])
actual_list = seek.find(exclude=[{"class": "gb1"}])
self.assertEqual(len(actual_list), page['exclude_links'])
def test_find_sort_by_href(self):
""" Sorting by href produces proper results """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(limit=5, sort=lambda key: key['href'] or "")
self.assertEqual(len(actual_list), len(page['limit_sort_href']))
for i, link in enumerate(actual_list):
self.assertDictSame(link, page['limit_sort_href'][i])
def test_find_sort_by_href(self):
""" Sorting by href produces proper results """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(limit=5, sort=lambda key: key['href'] or "")
self.assertEqual(len(actual_list), len(page['limit_sort_href']))
for i, link in enumerate(actual_list):
self.assertDictSame(link, page['limit_sort_href'][i])
def test_find_reverse_sort(self):
""" Ensure reverse sort sorts before limiting the # of links """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(limit=5, reverse=True)
self.assertEqual(len(actual_list), len(page['limit_reverse_find']))
for i, link in enumerate(actual_list):
self.assertDictSame(link, page['limit_reverse_find'][i])
def test_find_limit(self):
""" Check that the actual array with a limit matches the test data """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(limit=5)
self.assertEqual(len(actual_list), len(page['limit_find']))
for i, link in enumerate(actual_list):
self.assertDictSame(link, page['limit_find'][i])
def test_find(self):
""" Test how grabbing the hyperlinks are aggregated """
seek = Links(self.url)
# Each of these assertions should have their own test method.
self.assertRaises(Exception, seek.find, filters=['href', 'style'])
# ex: "test_find_hyperlink_bad_filter_param"
self.assertRaises(Exception, seek.find, filters=25)
self.assertEqual(len(seek.find(limit=5)), 5)
self.assertEqual(len(seek.find(limit=1)), 1)
def test_find_number_of_links(self):
""" Ensure expected number of links reflects actual number of links """
for page in td.pages:
seek = Links(text=page['text'])
self.assertEqual(len(seek.find()), page['num_links'])
def test_find_limit_param(self):
""" How does find() handle the limit property """
seek = Links(self.url)
self.assertEqual(len(seek.find(limit=5)), 5)
self.assertEqual(len(seek.find(limit=1)), 1)
def test_soup_property(self):
""" Getting the web page yields correct response"""
seek = Links(self.url)
self.assertIsInstance(seek._soup, bs4.BeautifulSoup)
def test_find_duplicates(self):
""" Determine if removing duplicates works """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(duplicates=False)
self.assertEqual(len(actual_list), page['duplicate_links'])
import re
from linkGrabber import Links
links = Links('http://google.com')
gb = links.find(limit=4, duplicates=False, pretty=True)
print(gb)
def test_find_number_of_links(self):
""" Ensure expected number of links reflects actual number of links """
for page in td.pages:
seek = Links(text=page['text'])
self.assertEqual(len(seek.find()), page['num_links'])
def test_find_limit_param(self):
""" How does find() handle the limit property """
seek = Links(self.url)
self.assertEqual(len(seek.find(limit=5)), 5)
self.assertEqual(len(seek.find(limit=1)), 1)
def test_find_duplicates(self):
""" Determine if removing duplicates works """
for page in td.pages:
seek = Links(text=page['text'])
actual_list = seek.find(duplicates=False)
self.assertEqual(len(actual_list), page['duplicate_links'])
def scraper(url, level_target=0, to=None, sameroot=False, overwrite=False):
level = 0
perlevel = defaultdict(list)
perlevel[0].append(url)
visited = defaultdict(int)
visited[url] = True
siteinfo = urlparse(url)
total = defaultdict(int) # total per level
finished = 0
while level <= level_target:
if not len(perlevel[level]) > 0:
level += 1
continue
url_actual = perlevel[level].pop()
msg = "[level:{}] [#:{}/{}]"
idx = total[level] - len(perlevel[level])
log.info(msg.format(level, idx, total[level]))
log.info(url_actual)
page = None
dirpath = os.path.join(to, str(level))
make_dir(dirpath)
archivo = encoding_path(url_actual)
for c in tablereplace:
archivo = archivo.replace(c, "_")
log.debug("using as filename:")
archivo = os.path.join(dirpath, archivo)
log.debug(archivo)
try:
from_file = InfoFile(archivo)
txt_path = "".join([from_file.dirname, os.sep, from_file.name, ".txt"])
to_txt = InfoFile(txt_path)
try:
page = Links(href=url_actual)
links = page.find(duplicates=False)
except Exception, e:
log.error("[FAIL] %s" % e)
continue
if not page:
log.info("The page apparently does not have links.")
continue
# process url
if not overwrite and os.path.exists(to_txt.path):
log.info("[OK] Text file already exists")
finished += 1
else:
try:
save_text(from_file, to_txt, page.response.content)
log.info("[OK] Status: %s" % page.response.status_code)
finished += 1
except Exception, e:
log.error(e)
log.error("[FAIL] Status: %s" % page.response.status_code)
print("urls added: ", end="")
for _url in links:
if "href" not in _url:
continue
_url = urljoin(url, _url["href"])
if not visited[_url]:
visited[_url] = True
link = urlparse(_url)
if sameroot:
if link.netloc != siteinfo.netloc:
continue
perlevel[level + 1].append(_url)
total[level + 1] += 1
print("*", end="")
print()
def test_page(self):
""" Getting the web page yields correct response"""
seek = Links(self.url)
self.assertIsInstance(seek._page(), bs4.BeautifulSoup)
