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
| from bs4 import BeautifulSoup
import urllib.request
import urllib.parse
url='https://blog.xinhaojin.top'
resp=urllib.request.urlopen(url)
data=resp.read()
html=data.decode()
soup=BeautifulSoup(html,'lxml')
tag=soup.find('title')
print(type(tag),tag)
tags=soup.find_all('a')
for tag in tags:
print(tag)
tags=soup.find_all('div',attrs={'class':"entry excerpt entry-summary"})
for tag in tags:
print(tag)
tags=soup.find_all(name=None,attrs={'class':"entry excerpt entry-summary"})
for tag in tags:
print(tag)
print(tag['class'])
print(tag.text)
def myFilter(tag):
return (tag.name=='a' and tag.has_attr("href") and tag['href']=="https://blog.xinhaojin.top/2020/08/")
tag=soup.find_all(myFilter)
print(tag)
|