html_dom.html_dom_graph_model() - Code Metrics - Inspection of "updates" - erivlis/graphinate - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — main ( ced03c...e8bc85 )

by Eran

created 2025-02-24 21:49 UTC

html_dom.html_dom_graph_model() B

↳ Parent: html_dom

Complexity

Conditions

Size

Total Lines	32
Code Lines	25

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	8
eloc	25
nop	1
dl	0
loc	32
rs	7.3333
c	0
b	0
f	0

import base64

import requests
from bs4 import BeautifulSoup, Tag

import graphinate


def load_html_from_url(url="https://www.google.com"):
    response = requests.get(url)
    return response.text


def load_html(file_path):
    with open(file_path) as file:
        return file.read()


def html_dom_graph_model(html_content):
    graph_model = graphinate.model(name="HTML DOM Graph")
    soup = BeautifulSoup(html_content, 'html.parser')

    def node_type(tag: Tag):
        return tag.name.strip('[]')

    def node_key(tag: Tag):
        return str((tag.sourceline, tag.sourcepos)) if isinstance(tag, Tag) else base64.b64encode(
            tag.encode()).decode()

    def node_label(tag: Tag):
        return str(tag)

    @graph_model.node(node_type, key=node_key, label=node_label)
    def html_node():
        for tag in soup.descendants:
            if tag.name is not None:
                yield tag

    @graph_model.edge()
    def contains():
        for tag in soup.descendants:
            if tag.name is not None:
                for child in tag.children:
                    if child.name is not None:
                        yield {
                            'source': node_key(tag),
                            'target': node_key(child)
                        }

    return graph_model


if __name__ == '__main__':
    html_content = load_html_from_url()
    dom_model = html_dom_graph_model(html_content)
    graphinate.materialize(
        dom_model,
        builder=graphinate.builders.GraphQLBuilder,
        builder_output_handler=graphinate.graphql
    )



1			import base64
2
3			import requests
4			from bs4 import BeautifulSoup, Tag
5
6			import graphinate
7
8
9			def load_html_from_url(url="https://www.google.com"):
10			response = requests.get(url)
11			return response.text
12
13
14			def load_html(file_path):
15			with open(file_path) as file:
16			return file.read()
17
18
19			def html_dom_graph_model(html_content):
20			graph_model = graphinate.model(name="HTML DOM Graph")
21			soup = BeautifulSoup(html_content, 'html.parser')
22
23			def node_type(tag: Tag):
24			return tag.name.strip('[]')
25
26			def node_key(tag: Tag):
27			return str((tag.sourceline, tag.sourcepos)) if isinstance(tag, Tag) else base64.b64encode(
28			tag.encode()).decode()
29
30			def node_label(tag: Tag):
31			return str(tag)
32
33			@graph_model.node(node_type, key=node_key, label=node_label)
34			def html_node():
35			for tag in soup.descendants:
36			if tag.name is not None:
37			yield tag
38
39			@graph_model.edge()
40			def contains():
41			for tag in soup.descendants:
42			if tag.name is not None:
43			for child in tag.children:
44			if child.name is not None:
45			yield {
46			'source': node_key(tag),
47			'target': node_key(child)
48			}
49
50			return graph_model
51
52
53			if __name__ == '__main__':
54			html_content = load_html_from_url()
55			dom_model = html_dom_graph_model(html_content)
56			graphinate.materialize(
57			dom_model,
58			builder=graphinate.builders.GraphQLBuilder,
59			builder_output_handler=graphinate.graphql
60			)
61
62

erivlis / graphinate

Push — main ( ced03c...e8bc85 )

html_dom.html_dom_graph_model() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like