1+ from bs4 import BeautifulSoup
2+
3+ html_doc = """
4+ <html><head><title>index</title></head>
5+ <body>
6+ <p class="title"><b>首页</b></p>
7+ <p class="main">我常用的网站
8+ <a href="https://www.google.com" class="website" id="google">Google</a>
9+ <a href="https://www.baidu.com" class="website" id="baidu">Baidu</a>
10+ <a href="https://cn.bing.com" class="website" id="bing">Bing</a>
11+ </p>
12+ <div><!--这是注释内容--></div>
13+ <p class="content1">...</p>
14+ <p class="content2">...</p>
15+ </body>
16+ """
17+
18+ # demo 1
19+ soup = BeautifulSoup (html_doc , "lxml" )
20+ tags = soup .find_all ('b' )
21+ print (tags )
22+
23+
24+ # demo 2
25+ import re
26+ for tag in soup .find_all (re .compile ("^b" )):
27+ print (tag .name )
28+
29+
30+ # demo 3
31+ for tag in soup .find_all (['a' , 'b' ]):
32+ print (tag )
33+
34+
35+ # demo 4
36+ for tag in soup .find_all (True ):
37+ print (tag .name , end = ', ' )
38+
39+
40+ # demo 5
41+ def has_id_class (tag ):
42+ return tag .has_attr ('id' ) and tag .has_attr ('class' )
43+
44+ tags = soup .find_all (has_id_class )
45+ for tag in tags :
46+ print (tag )
47+
48+
49+ # demo 6
50+ tags = soup .find_all (id = 'google' )
51+ print (tags [0 ]['href' ])
52+
53+ for tag in soup .find_all (id = True ):
54+ print (tag ['href' ])
55+
56+
57+ # demo 7
58+ tags = soup .find_all ("a" , class_ = "website" )
59+ for tag in tags :
60+ print (tag ['href' ])
61+
62+ def has_seven_characters (css_class ):
63+ return css_class is not None and len (css_class ) == 7
64+
65+ for tag in soup .find_all (class_ = has_seven_characters ):
66+ print (tag ['id' ])
67+
68+
69+ # demo 8
70+ css_soup = BeautifulSoup ('<p class="body strikeout"></p>' , 'lxml' )
71+ tags = css_soup .find_all ("p" , class_ = "strikeout" )
72+ print (tags )
73+
74+
75+ # demo 9
76+ tags = soup .find_all (text = "Google" )
77+ print ("google : " , tags )
78+
79+ tags = soup .find_all (text = ["Baidu" , "Bing" ])
80+ print ("baidu & bing : " , tags )
81+
82+ tags = soup .find_all ('a' , text = "Google" )
83+ print ("a[text=google] : " , tags )
84+
85+
86+ # demo 10
87+ tag = soup .find_all ("a" , limit = 1 )
88+ print (tag )
89+
90+ tags = soup .find_all ("p" , recursive = False )
91+ print (tags )
92+
93+
94+ # demo 11
95+ tags = soup .select ("body a" )
96+ for tag in tags :
97+ print (tag ['href' ])
98+
99+
100+ # demo 12
101+ tags = soup .select ("p > a" )
102+ print (tags )
103+
104+ tags = soup .select ("p > #google" )
105+ print (tags )
106+
107+
108+ # demo 13
109+ tags = soup .select (".website" )
110+ for tag in tags :
111+ print (tag .string )
112+
113+
114+ # demo 14
115+ tags = soup .select ("#google" )
116+ print (tags )
117+
118+
119+ # demo 15
120+ tags = soup .select ('a[href="https://cn.bing.com"]' )
121+ print (tags )
0 commit comments