1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
| headers = {'User-Agent': 'Mozilla/5.0'}
#from html.parser import HTMLParser
#from urllib.request import urlopen
#
#req = ("https://www.nyrr.org/charities-clubs-and-community/local-clubs/club-listing/3runpl", headers = {'User-Agent': 'Mozilla/5.0'})
#
#content = urlopen(req).read()
#
#class Parser(HTMLParser):
# def __init__(self):
# super().__init__()
# self.in_contact = False
# self.in_value = False
# self.info = False
# self.facebook = False
#
# def handle_starttag(self, tag, attrs):
# if tag == "div":
# for att in attrs:
# if att[0] == 'class' and att[1] == "contactbox":
# self.in_contact = True
#
# elif self.in_contact and tag == "p":
# self.in_value = True
#
# elif self.in_value and tag == "a":
# for att in attrs:
# if att[0] == 'href':
# self.facebook = att[1]
# self.in_contact = False
# self.in_value = False
#
# def handle_endtag(self, tag):
# if self.in_contact and tag == "div":
# self.in_contact = False
# self.in_value = False
#
# def handle_data(self, data):
# if self.in_value:
# txt = data.strip()
# if txt and txt.replace(" ", "").isdecimal():
# self.info = txt
#
#
#
#parser = Parser()
#parser.feed(content)
#print("Contact info: %s" % parser.info)
# print("Facebook: %s" % parser.facebook) |
Partager