def test_fixlinks_fragment():
"""Links with fragment part to included pages should not be marked as 'nopo'."""
chosen_pages = {'foo'}
html = '<a href="/wiki/foo#bar></a>'
soup = bs4.BeautifulSoup(html, 'lxml')
a_tag = soup.find('a')
ImageParser.fixlinks(a_tag, chosen_pages)
assert a_tag.attrs.get('class') is None
def test_fixlinks_nopo(name):
"""Test that wiki links to not included pages are marked with the 'nopo' class."""
chosen_pages = {'eggs', 'spam'}
html = '<a href="/wiki/{}"></a>'.format(name)
soup = bs4.BeautifulSoup(html, 'lxml')
a_tag = soup.find('a')
ImageParser.fixlinks(a_tag, chosen_pages)
assert a_tag.attrs.get('class') == ['nopo']
def test_fixlinks_no_nopo(name):
"""Test that wiki links to included pages are not marked with the 'nopo' class."""
fname = to3dirs.to_filename(name)
chosen_pages = {fname}
url = urllib.parse.quote(name)
html = '<a href="/wiki/{}"></a>'.format(url)
soup = bs4.BeautifulSoup(html, 'lxml')
a_tag = soup.find('a')
ImageParser.fixlinks(a_tag, chosen_pages)
assert a_tag.attrs.get('class') is None
def test_no_size_querystring_when_size_undefined():
soup = bs4.BeautifulSoup(features="html.parser")
url = ("//upload.wikimedia.org/wikipedia/commons/"
"thumb/4/40/P_ps.png/35px-P_ps.png")
tag = soup.new_tag("img", src=url)
ImageParser.replace(tag)
assert tag.attrs['src'].endswith(".png")
def test_included_pages_links():
original_html = load_fixture('article_with_inlinemath.html')
html, _ = ImageParser.parse_html(original_html, chosen_pages=set())
soup1 = bs4.BeautifulSoup(html, "lxml")
html, _ = ImageParser.parse_html(original_html,
chosen_pages={"Wikcionario"})
soup2 = bs4.BeautifulSoup(html, "lxml")
no_chosen_pages_count = len(soup1.find_all("a", "nopo"))
assert no_chosen_pages_count - 1 == len(soup2.find_all("a", "nopo"))
def test_append_size_querystring():
soup = bs4.BeautifulSoup(features="html.parser")
url = ("//upload.wikimedia.org/wikipedia/commons/"
"thumb/4/40/P_ps.png/35px-P_ps.png")
tag = soup.new_tag("img", src=url, width='100px', height='50px')
ImageParser.replace(tag)
assert tag.attrs.get("width") is None
assert tag.attrs.get("height") is None
assert tag.attrs['src'].endswith("?s=100px-50px")
def test_parse_html():
html = load_fixture('article_with_inlinemath.html')
base_soup = bs4.BeautifulSoup(html, features="html.parser")
html, _ = ImageParser.parse_html(html, chosen_pages=set())
soup = bs4.BeautifulSoup(html, features="html.parser")
assert len(soup.find_all("img")) == 7
assert len(soup.find_all("a")) == 221
assert len(soup.find_all("a", "external")) == 8
# no link starting with //
assert any(
[tag.attrs['href'].startswith("//") for tag in soup.find_all("a")])
assert "data-file-width" not in html
assert "data-file-height" not in html
# check that the "image links" are removed
assert len(base_soup.find_all("a", "image")) != 0
assert len(soup.find_all("a", "image")) == 0
# check that the only image removed is "Special:CentralAutoLogin"
assert len(soup.find_all("img")) == len(base_soup.find_all("img")) - 1
assert any(
["AutoLogin" in tag.attrs["src"] for tag in base_soup.find_all("img")])
assert not any(
["AutoLogin" in tag.attrs["src"] for tag in soup.find_all("img")])
def test_parse_html_remove_selflinks():
link_without_href = '<a class="mw-selflink selflink">Argentina</a>'
html, _ = ImageParser.parse_html(link_without_href, chosen_pages=set())
# check that links without href are removed
soup = bs4.BeautifulSoup(html, "lxml")
assert len(soup.find_all("a", href=None)) == 0
assert 'Argentina' in html
def _check(self, url, should_web, should_dsk):
"""Do proper checking."""
tag = self.soup.new_tag("img", src=url)
dsk, web = ImageParser.replace(tag)
self.assertEqual(web, should_web)
self.assertEqual(dsk, should_dsk)
self.assertEqual(tag.attrs["src"], '/images/' + should_dsk)