def _collect_link_data(self, link_sources, link_targets):
link_targets.add(self.url)
if not self.url.endswith(".html"):
return
root = _XML(_read_file(self._output_path))
for elem in root.iter("*"):
for name in ("href", "src", "action"):
try:
url = elem.attrib[name]
except KeyError:
continue
split_url = _urlparse.urlsplit(url)
if split_url.scheme or split_url.netloc:
continue
normalized_url = _urlparse.urljoin(
self.url, _urlparse.urlunsplit(split_url))
link_sources[normalized_url].add(self)
for elem in root.iter("*"):
if "id" in elem.attrib:
normalized_url = _urlparse.urljoin(self.url,
f"#{elem.attrib['id']}")
if normalized_url in link_targets:
self.site.warn("Duplicate link target in '{}'",
normalized_url)
link_targets.add(normalized_url)
def html_table_functions():
data = (
(1, 2, 3),
("a", "b", "c"),
(None, "", 0),
)
_XML(_html_table(data))
_XML(_html_table(data, headings=("A", "B", "C")))
with working_dir():
with open("test.csv", "w", newline="") as f:
writer = _csv.writer(f)
writer.writerows(data)
_XML(_html_table_csv("test.csv"))
def find_links(self):
if not self.output_path.endswith(".html"):
return
self.site.info("Finding links in {}", self)
self._load_output()
try:
root = _XML(self.content)
except Exception as e:
self.site.info(str(e))
return
assert root is not None, self.content
links = self._gather_links(root)
link_targets = self._gather_link_targets(root)
for link in links:
if link == "?":
continue
scheme, netloc, path, query, fragment = _urlsplit(link)
if scheme and scheme not in ("file", "http", "https", "ftp"):
continue
if netloc in ("issues.apache.org", "bugzilla.redhat.com"):
continue
if (fragment and not path) or not path.startswith("/"):
link = _urljoin(self.url, link)
self.site.links[link].add(self.url)
self.site.link_targets.update(link_targets)