def is_file(cls, file):
'''Return whether the file is likely a Sitemap.'''
peeked_data = wpull.util.peek_file(file)
if is_gzip(peeked_data):
try:
peeked_data = wpull.decompression.gzip_uncompress(
peeked_data, truncated=True)
except zlib.error:
pass
peeked_data = wpull.string.printable_bytes(peeked_data)
if b'<?xml' in peeked_data \
and (b'<sitemapindex' in peeked_data or b'<urlset' in peeked_data):
return True
def is_file(cls, file):
'''Return whether the file is likely a Sitemap.'''
peeked_data = wpull.util.peek_file(file)
if is_gzip(peeked_data):
try:
peeked_data = wpull.decompression.gzip_uncompress(
peeked_data, truncated=True
)
except zlib.error:
pass
peeked_data = wpull.string.printable_bytes(peeked_data)
if b'<?xml' in peeked_data \
and (b'<sitemapindex' in peeked_data or b'<urlset' in peeked_data):
return True
def iter_links(self, file, encoding=None):
peeked_data = wpull.util.peek_file(file)
if is_gzip(peeked_data):
file = gzip.GzipFile(mode='rb', fileobj=file)
if self.is_file(file):
for html_obj in self._html_parser.parse(file, encoding):
if isinstance(html_obj, Element) \
and html_obj.tag.endswith('loc'):
if html_obj.text:
yield html_obj.text
else:
parser = robotexclusionrulesparser.RobotExclusionRulesParser()
parser.parse(file.read(self.MAX_ROBOTS_FILE_SIZE))
for link in parser.sitemaps:
yield link
def iter_links(self, file, encoding=None):
peeked_data = wpull.util.peek_file(file)
if is_gzip(peeked_data):
file = gzip.GzipFile(mode='rb', fileobj=file)
if self.is_file(file):
for html_obj in self._html_parser.parse(file, encoding):
# Beware: some .tag values are not a str:
# html_obj=<?xml version="1.0" encoding="UTF-8" ?>
# tag=<cyfunction ProcessingInstruction at 0x7f17e49d78e8>
if isinstance(html_obj, Element) and \
isinstance(html_obj.tag, str) and \
html_obj.tag.endswith('loc'):
if html_obj.text:
yield html_obj.text
else:
parser = robotexclusionrulesparser.RobotExclusionRulesParser()
parser.parse(file.read(self.MAX_ROBOTS_FILE_SIZE))
for link in parser.sitemaps:
yield link
