python pyquery库_Python爬虫之pyquery库的基本使用

1 #兄弟元素

2 html = '''

3

4

5

• 6
• first item7
• second item8
• third item9
• fourth item10
• fifthth item11

12

13

14 '''

15 from pyquery importPyQuery as pq16 doc =pq(html)17 #注意下面item-0后面直接是. 没有空格

18 li = doc('.list .item-0.active')19 print(li.siblings())20

21 print(li.siblings('.active'))22

23 #遍历

24 #单个元素

25 html = '''

26

27

28

• 29
• first item30
• second item31
• third item32
• fourth item33
• fifthth item34

35

36

37 '''

38 from pyquery importPyQuery as pq39 doc =pq(html)40 li = doc('.item-0.active')41 print(li)42

43 html = '''

44

45

46

• 47
• first item48
• second item49
• third item50
• fourth item51
• fifthth item52

53

54

55 '''

56 from pyquery importPyQuery as pq57 doc =pq(html)58 lis = doc('li').items()59 print(type(lis))60 for li inlis:61 print(li)62

63 #获取信息

64 #获取属性

65 html = '''

66

67

68

• 69
• first item70
• second item71
• third item72
• fourth item73
• fifthth item74

75

76

77 '''

78 from pyquery importPyQuery as pq79 doc =pq(html)80 a = doc('.item-0.active a')81 print(a)82 #获取属性的两种方法

83 print(a.attr('href'))84 print(a.attr.href)85

86 #获取文本

87 print(a.text())88

89 #获取html

90 from pyquery importPyQuery as pq91 doc =pq(html)92 li = doc('.item-0.active')93 print(li)94 #得到

标签里面的代码

95 print(li.html())96

97 #DOM操作

98 #addClass、removeClass

99 from pyquery importPyQuery as pq100 doc =pq(html)101 li = doc('.item-0.active')102 print(li)103 li.remove_class('active')104 print(li)105 li.add_class('active')106 print(li)107

108 #attr CSS

109 li.attr('name', 'link')110 print(li)111 li.css('font-size', '14px')112 print(li)113

114 #remove

115 html = '''

116

117 Hello,World118

This is a paragraph

119

120 '''

121 from pyquery importPyQuery as pq122 doc =pq(html)123 wrap = doc('.wrap')124 print(wrap.text())125 wrap.find('p').remove()126 print(wrap.text())127

128 #伪类选择器

129 html = '''

130

131

132

• 133
• first item134
• second item135
• third item136
• fourth item137
• fifthth item138

139

140

141 '''

142 from pyquery importPyQuery as pq143 doc =pq(html)144 #获取第一个元素

145 li = doc('li:first-child')146 print(li)147 #获取最后一个元素

148 li = doc('li:last-child')149 print(li)150 #获取第二个元素

151 li = doc('li:nth-child(2)')152 print(li)153 #获取下标为2的元素后面的所有元素(下标从0开始)

154 li = doc('li:gt(2)')155 print(li)156 #获取下标为偶数的元素

157 li = doc('li:nth-child(2n)')158 print(li)159 #获取内容包含second 的元素

160 li = doc('li:contains(second)')161 print(li)