Python 爬虫 提取整个页面的 链接 通用
提取整个页面的 链接 通用
Python
from html.parser import HTMLParser
from urllib import parse
import requests
class LinkFinder(HTMLParser):
def __init__(self, base_url, page_url):
super().__init__()
self.base_url = base_url
self.page_url = page_url
self.links = set()
# When we call HTMLParser feed() this function is called when it
# encounters an opening tag <a>
def handle_starttag(self, tag, attrs):
if tag == 'a':
for (attribute, value) in attrs:
if attribute == 'href':
url = parse.urljoin(self.base_url, value)
if self.base_url in url:
self.links.add(url)
# exclud
def page_links(self):
return self.links
def error(self, message):
pass
if __name__ == '__main__':
finder = LinkFinder("https://www.csai.cn", 'https://www.csai.cn/baoxian/')
r = requests.get("https://www.csai.cn/baoxian/")
finder.feed(r.text)
urls = list(set(finder.page_links()))
print(urls)
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
|
from html.parser import HTMLParser
from urllib import parse
import requests
class LinkFinder(HTMLParser):
def __init__(self, base_url, page_url):
super().__init__()
self.base_url = base_url
self.page_url = page_url
self.links = set()
# When we call HTMLParser feed() this function is called when it
# encounters an opening tag <a>
def handle_starttag(self, tag, attrs):
if tag == 'a':
for (attribute, value) in attrs:
if attribute == 'href':
url = parse.urljoin(self.base_url, value)
if self.base_url in url:
self.links.add(url)
# exclud
def page_links(self):
return self.links
def error(self, message):
pass
if __name__ == '__main__':
finder = LinkFinder("https://www.csai.cn", 'https://www.csai.cn/baoxian/')
r = requests.get("https://www.csai.cn/baoxian/")
finder.feed(r.text)
urls = list(set(finder.page_links()))
print(urls)
|
效果如图
-
zeropython 微信公众号
5868037 QQ号
[email protected] QQ邮箱