def parse_html(page_url):
html_string = ''
try:
response = urlopen(page_url, timeout=5)
if 'text/html' in response.getheader('Content-Type'):
html_bytes = response.read()
html_string = html_bytes.decode("utf-8")
finder = HtmlParser(Spider.base_url, page_url)
finder.feed(html_string)
except Exception as e:
print(str(e))
return set(), html_string
return finder.page_links(), html_string
def parse_html(self):
"""
parse_html - Parse the html content
"""
try:
parser = HtmlParser(self.url)
parser.set_pattern(self.pattern)
parser.set_urls(self.spider_config)
parser.set_next_depth(self.depth)
parser.feed(self.page)
parser.close()
except UnicodeDecodeError as e:
logging.error('Thread:{} parse {} failed, msg:{}'.format(
self.thread_id, self.url, e))
return False
return True