franciscobatista356

## avengers_wiki.json
{"ns": 0,
 "pageid": 44254295,
 "terms": {"alias": ["Avengers Endgame", "Avengers End Game", "Avengers 4"],
           "description": ["2019 superhero film produced by Marvel Studios"],
           "label": ["Avengers: Endgame"]},
 "title": "Avengers: Endgame"}


## get_canonical_path.py
from requests_html import HTMLSession

#Builds a DOM path recursively
def build_dom_path(element, path):

  if element is None:
    return path
  else:
    path.append(element.tag)


## index-canonical-moved.html
<!doctype html>

<html lang="en">
<head>
  <meta charset="utf-8">

  <title>This is a test</title>
  <link rel="canonical" href="http://localhost">
  <meta name="description" content="This is a test">
  <meta name="author" content="Hamlet Batista">

## index-invalid-script-head.html
<!doctype html>

<html lang="en">
<head>
  <meta charset="utf-8">

  <title>This is a test</title>
  <meta name="description" content="This is a test">
  <meta name="author" content="Hamlet Batista">

## index-invalid-head.html
<!doctype html>

<html lang="en">
<head>
  <meta charset="utf-8">

  <title>This is a test</title>
  <meta name="description" content="This is a test">
  <meta name="author" content="Hamlet Batista">

## index-no-body.html
<!doctype html>

<html lang="en">
<head>
  <meta charset="utf-8">

  <title>This is a test</title>
  <meta name="description" content="This is a test">
  <meta name="author" content="Hamlet Batista">
	{"ns": 0,
	"pageid": 44254295,
	"terms": {"alias": ["Avengers Endgame", "Avengers End Game", "Avengers 4"],
	"description": ["2019 superhero film produced by Marvel Studios"],
	"label": ["Avengers: Endgame"]},
	"title": "Avengers: Endgame"}
	from requests_html import HTMLSession

	#Builds a DOM path recursively
	def build_dom_path(element, path):

	if element is None:
	return path
	else:
	path.append(element.tag)
	<!doctype html>

	<html lang="en">
	<head>
	<meta charset="utf-8">

	<title>This is a test</title>
	<link rel="canonical" href="http://localhost">
	<meta name="description" content="This is a test">
	<meta name="author" content="Hamlet Batista">