爬虫之BeautifulSoup
BeautifulSoup是一个模块，该模块用于接收一个HTML或XML字符串，然后将其进行格式化，之后便可以使用他提供的方法进行快速查找指定元素，从而使得在HTML或XML中查找指定元素变得简单。
from bs4 import BeautifulSoup html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> asdf <div class="title"> <b>The Dormouse's story总共</b> <h1>f</h1> </div> <div class="story">Once upon a time there were three little sisters; and their names were <a class="sister0" id="link1">Els<span>f</span>ie</a>, <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; and they lived at the bottom of a well.</div> ad<br/>sf <p class="story">...</p> </body> </html> """ soup = BeautifulSoup(html_doc, features="lxml") # 找到第一个a标签 tag1 = soup.find(name='a') # 找到所有的a标签 tag2 = soup.find_all(name='a') # 找到id＝link2的标签 tag3 = soup.select('#link2') 简单示例
1. name，标签名称
1 # tag = soup.find('a')
2 # name = tag.name # 获取
3 # print(name)
4 # tag.name = 'span' # 设置
5 # print(soup)
2. attr，标签属性
1 # tag = soup.find('a')
2 # attrs = tag.attrs # 获取
3 # print(attrs)
4 # tag.attrs = {'ik':123} # 设置
5 # tag.attrs['id'] = 'iiiii' # 设置
6 # print(soup)
3. children,所有子标签
1 # body = soup.find('body')
2 # v = body.children
4. descendants,所有子子孙孙标签
1 # body = soup.find('body')
2 # v = body.descendants
5. clear,将标签的所有子标签全部清空（保留标签名）
1 # tag = soup.find('body')
2 # tag.clear()
3 # print(soup)
6. decompose,递归的删除所有的标签
1 # body = soup.find('body')
2 # body.decompose()
3 # print(soup)
7. extract,递归的删除所有的标签，并获取删除的标签
1 # body = soup.find('body')
2 # v = body.extract()
3 # print(soup)
8. decode,转换为字符串（含当前标签）；decode_contents（不含当前标签）
1 # body = soup.find('body')
2 # v = body.decode()
3 # v = body.decode_contents()
4 # print(v)
9. encode,转换为字节（含当前标签）；encode_contents（不含当前标签）
1 # body = soup.find('body')
2 # v = body.encode()
3 # v = body.encode_contents()
4 # print(v)
10. find,获取匹配的第一个标签
1 # tag = soup.find('a')
2 # print(tag)
3 # tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
4 # tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
5 # print(tag)
11. find_all,获取匹配的所有标签
1 # tags = soup.find_all('a')
2 # print(tags)
3
4 # tags = soup.find_all('a',limit=1)
5 # print(tags)
6
7 # tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
8 # # tags = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
9 # print(tags)
10
11
12 # ####### 列表 #######
13 # v = soup.find_all(name=['a','div'])
14 # print(v)
15
16 # v = soup.find_all(class_=['sister0', 'sister'])
17 # print(v)
18
19 # v = soup.find_all(text=['Tillie'])
20 # print(v, type(v[0]))
21
22
23 # v = soup.find_all(id=['link1','link2'])
24 # print(v)
25
26 # v = soup.find_all(href=['link1','link2'])
27 # print(v)
28
29 # ####### 正则 #######
30 import re
31 # rep = re.compile('p')
32 # rep = re.compile('^p')
33 # v = soup.find_all(name=rep)
34 # print(v)
35
36 # rep = re.compile('sister.*')
37 # v = soup.find_all(class_=rep)
38 # print(v)
39
40 # rep = re.compile('http://www.oldboy.com/static/.*')
41 # v = soup.find_all(href=rep)
42 # print(v)
43
44 # ####### 方法筛选 #######
45 # def func(tag):
46 # return tag.has_attr('class') and tag.has_attr('id')
47 # v = soup.find_all(name=func)
48 # print(v)
49
50
51 # ## get,获取标签属性
52 # tag = soup.find('a')
53 # v = tag.get('id')
54 # print(v)
12. has_attr,检查标签是否具有该属性
1 # tag = soup.find('a')
2 # v = tag.has_attr('id')
3 # print(v)
13. get_text,获取标签内部文本内容
1 # tag = soup.find('a')
2 # v = tag.get_text('id')
3 # print(v)
14. index,检查标签在某标签中的索引位置
1 # tag = soup.find('body')
2 # v = tag.index(tag.find('div'))
3 # print(v)
4
5 # tag = soup.find('body')
6 # for i,v in enumerate(tag):
7 # print(i,v)
15. is_empty_element,是否是空标签(是否可以是空)或者自闭合标签，
判断是否是如下标签：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
1 # tag = soup.find('br')
2 # v = tag.is_empty_element
3 # print(v)
16. 当前的关联标签
1 # soup.next 2 # soup.next_element 3 # soup.next_elements 4 # soup.next_sibling 5 # soup.next_siblings 6 7 # 8 # tag.previous 9 # tag.previous_element 10 # tag.previous_elements 11 # tag.previous_sibling 12 # tag.previous_siblings 13 14 # 15 # tag.parent 16 # tag.parents
17. 查找某标签的关联标签
1 # tag.find_next(...) 2 # tag.find_all_next(...) 3 # tag.find_next_sibling(...) 4 # tag.find_next_siblings(...) 5 6 # tag.find_previous(...) 7 # tag.find_all_previous(...) 8 # tag.find_previous_sibling(...) 9 # tag.find_previous_siblings(...) 10 11 # tag.find_parent(...) 12 # tag.find_parents(...) 13 14 # 参数同find_all
18. select,select_one, CSS选择器
1 soup.select("title")
2
3 soup.select("p nth-of-type(3)")
4
5 soup.select("body a")
6
7 soup.select("html head title")
8
9 tag = soup.select("span,a")
10
11 soup.select("head > title")
12
13 soup.select("p > a")
14
15 soup.select("p > a:nth-of-type(2)")
16
17 soup.select("p > #link1")
18
19 soup.select("body > a")
20
21 soup.select("#link1 ~ .sister")
22
23 soup.select("#link1 + .sister")
24
25 soup.select(".sister")
26
27 soup.select("[class~=sister]")
28
29 soup.select("#link1")
30
31 soup.select("a#link2")
32
33 soup.select('a[href]')
34
35 soup.select('a[href="http://example.com/elsie"]')
36
37 soup.select('a[href^="http://example.com/"]')
38
39 soup.select('a[href$="tillie"]')
40
41 soup.select('a[href*=".com/el"]')
42
43
44 from bs4.element import Tag
45
46 def default_candidate_generator(tag):
47 for child in tag.descendants:
48 if not isinstance(child, Tag):
49 continue
50 if not child.has_attr('href'):
51 continue
52 yield child
53
54 tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator)
55 print(type(tags), tags)
56
57 from bs4.element import Tag
58 def default_candidate_generator(tag):
59 for child in tag.descendants:
60 if not isinstance(child, Tag):
61 continue
62 if not child.has_attr('href'):
63 continue
64 yield child
65
66 tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1)
67 print(type(tags), tags)
19. 标签的内容
1 # tag = soup.find('span')
2 # print(tag.string) # 获取
3 # tag.string = 'new content' # 设置
4 # print(soup)
5
6 # tag = soup.find('body')
7 # print(tag.string)
8 # tag.string = 'xxx'
9 # print(soup)
10
11 # tag = soup.find('body')
12 # v = tag.stripped_strings # 递归内部获取所有标签的文本
13 # print(v)
20.append在当前标签内部追加一个标签
1 # tag = soup.find('body')
2 # tag.append(soup.find('a'))
3 # print(soup)
4 #
5 # from bs4.element import Tag
6 # obj = Tag(name='i',attrs={'id': 'it'})
7 # obj.string = '我是一个新来的'
8 # tag = soup.find('body')
9 # tag.append(obj)
10 # print(soup)
21.insert在当前标签内部指定位置插入一个标签
1 # from bs4.element import Tag
2 # obj = Tag(name='i', attrs={'id': 'it'})
3 # obj.string = '我是一个新来的'
4 # tag = soup.find('body')
5 # tag.insert(2, obj)
6 # print(soup)
22. insert_after,insert_before 在当前标签后面或前面插入
1 # from bs4.element import Tag
2 # obj = Tag(name='i', attrs={'id': 'it'})
3 # obj.string = '我是一个新来的'
4 # tag = soup.find('body')
5 # # tag.insert_before(obj)
6 # tag.insert_after(obj)
7 # print(soup)
23. replace_with 在当前标签替换为指定标签
1 # from bs4.element import Tag
2 # obj = Tag(name='i', attrs={'id': 'it'})
3 # obj.string = '我是一个新来的'
4 # tag = soup.find('div')
5 # tag.replace_with(obj)
6 # print(soup)
24. 创建标签之间的关系（但不会改变标签的位置）
1 # tag = soup.find('div')
2 # a = soup.find('a')
3 # tag.setup(previous_sibling=a)
4 # print(tag.previous_sibling)
25. wrap，将指定标签把当前标签包裹起来
1 # from bs4.element import Tag
2 # obj1 = Tag(name='div', attrs={'id': 'it'})
3 # obj1.string = '我是一个新来的'
4 #
5 # tag = soup.find('a')
6 # v = tag.wrap(obj1)
7 # print(soup)
8
9 # tag = soup.find('a')
10 # v = tag.wrap(soup.find('p'))
11 # print(soup)
26. unwrap，去掉当前标签，将保留其包裹的标签
1 # tag = soup.find('a')
2 # v = tag.unwrap()
3 # print(soup)
