To browse HTML document parsed by BeautifulSoup with DFS or BFS do :
solution.py:
import bs4
from bs4 import BeautifulSoup
html = """
<div>root
<div>child1
<div>child4
</div>
<div>child5
</div>
</div>
<div>child2
</div>
<div>child3
<div>child6
</div>
</div>
</div>
"""
Append these lines to solution.py :
def visit(node):
if isinstance(node, bs4.element.Tag):
# be careful bs4.element subclass ...
print(type(node), 'tag:', node.name)
elif isinstance(node, bs4.element.NavigableString):
# be careful bs4.CDdata and bs4.element.Comment subclass ...
print(type(node), repr(node.string))
else:
print(type(node), 'UNKNOWN')
And:
def dfs(html):
bs = BeautifulSoup(html, 'html.parser')
# <class 'bs4.BeautifulSoup'> [document]
visit(bs)
for child in bs.recursiveChildGenerator():
visit(child)
def bfs(html):
bs = BeautifulSoup(html, 'html.parser')
# <class 'bs4.BeautifulSoup'> [document]
visit(bs)
for child in recursiveChildGeneratorBfs(bs):
visit(child)
def recursiveChildGeneratorBfs(bs):
root = bs
stack = [root]
while len(stack) != 0:
node = stack.pop(0)
if node is not bs:
yield node
if hasattr(node, 'children'):
for child in node.children:
stack.append(child)
In ipython
console:
In [1]: run solution.py
BFS:
In [2]: bfs(html)
<class 'bs4.BeautifulSoup'> tag: [document]
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.NavigableString'> 'root\n '
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.NavigableString'> 'child1\n '
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.NavigableString'> 'child2\n '
<class 'bs4.element.NavigableString'> 'child3\n '
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.NavigableString'> 'child4\n '
<class 'bs4.element.NavigableString'> 'child5\n '
<class 'bs4.element.NavigableString'> 'child6\n '
DFS:
In [3]: dfs(html)
<class 'bs4.BeautifulSoup'> tag: [document]
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> 'root\n '
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> 'child1\n '
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> 'child4\n '
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> 'child5\n '
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> 'child2\n '
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> 'child3\n '
<class 'bs4.element.Tag'> tag: div
<class 'bs4.element.NavigableString'> 'child6\n '
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.NavigableString'> '\n'
<class 'bs4.element.NavigableString'> '\n'
See :
Documentation