def iter_links(self):
"""Yields all links in the page"""
document = html5lib.parse(
self.content,
transport_encoding=_get_encoding_from_headers(self.headers),
namespaceHTMLElements=False,
)
base_url = _determine_base_url(document, self.url)
for anchor in document.findall(".//a"):
if anchor.get("href"):
href = anchor.get("href")
url = _clean_link(urllib_parse.urljoin(base_url, href))
pyrequire = anchor.get('data-requires-python')
pyrequire = unescape(pyrequire) if pyrequire else None
yield Link(url, self.url, requires_python=pyrequire)
def __init__(self, content, url, headers=None):
# Determine if we have any encoding information in our headers
encoding = None
if headers and "Content-Type" in headers:
content_type, params = cgi.parse_header(headers["Content-Type"])
if "charset" in params:
encoding = params['charset']
self.content = content
self.parsed = html5lib.parse(
self.content,
transport_encoding=encoding,
namespaceHTMLElements=False,
)
self.url = url
self.headers = headers
def __init__(self, content, url, headers=None):
# Determine if we have any encoding information in our headers
encoding = None
if headers and "Content-Type" in headers:
content_type, params = cgi.parse_header(headers["Content-Type"])
if "charset" in params:
encoding = params['charset']
self.content = content
self.parsed = html5lib.parse(
self.content,
transport_encoding=encoding,
namespaceHTMLElements=False,
)
self.url = url
self.headers = headers
def parse_links(page: "HTMLPage") -> Iterable[Link]:
"""
Parse an HTML document, and yield its anchor elements as Link objects.
"""
document = html5lib.parse(
page.content,
transport_encoding=page.encoding,
namespaceHTMLElements=False,
)
url = page.url
base_url = _determine_base_url(document, url)
for anchor in document.findall(".//a"):
link = _create_link_from_element(
anchor,
page_url=url,
base_url=base_url,
)
if link is None:
continue
yield link