def seo(request):
#output = analyze('https://seositecheckup.com/', 'https://www.marketgoal.com/sitemap_index.xml')
output = analyze('http://www.feedbackinfra.com/contact.php')
customList = []
for keys, song in output.items():
#for datain in song:
if type(song) == type([]):
for datain in song:
#if datain.get('url') != 'None':
customList.append(datain)
return render(request, 'about/seo.html', {'seoData': customList})
def test_print_output():
output = analyze('https://www.sethserver.com/tests/utf8.html')
assert len(output['pages']) == 1
assert output['pages'][0][
'url'] == 'https://www.sethserver.com/tests/utf8.html'
assert output['pages'][0]['title'] == 'unicode chara¢ters'
assert output['pages'][0]['description'] == ''
assert output['pages'][0]['word_count'] == 493
assert output['errors'] == []
assert output['duplicate_pages'] == []
def index(request):
domain = whois.whois('marketgoal.com')
xml = urllib.request.urlopen(
'http://data.alexa.com/data?cli=11&dat=s&url={}'.format(
"www.marketgoal.com")).read()
result = xmltodict.parse(xml)
data = json.dumps(result).replace("@", "")
data_tojson = json.loads(data)
# html = """
# <div>hello</div>
# <a href="/index.html">Not this one</a>"
# <a href="http://google.com">Link 1</a>
# <a href="http:/amazon.com">Link 2</a>
# """
# soup = BeautifulSoup('http://marketgoal.com')
# http_links = soup.findAll('a', href=re.compile(r"^http"))
# results = [a for a in http_links if a['href'].find('google') == -1]
# print(results)
# obj = CallAwis('AKIAJA5H7O5EY24LS5HQ' , '3NO5p4ebYtkwPaDavcLpgNUd+pwItyTYhlrvlHgd')
# obj=CallAwis('AKIAJA5H7O5EY24LS5HQ','3NO5p4ebYtkwPaDavcLpgNUd+pwItyTYhlrvlHgd')
# allalexaData = obj.urlinfo('http://www.pageturnpro.com/')
# allalexaData = json.loads(json.dumps(xmltodict.parse(str(allalexaData))))
# alexaRand = {}
# for key,value in allalexaData['aws:UrlInfoResponse']['aws:Response']['aws:UrlInfoResult']['aws:Alexa'].items():
# if key == 'aws:TrafficData':
# alexaRand['Rank'] = value['aws:Rank']
# alexaRand['RankUs'] = value['aws:RankByCountry']['aws:Country']
#xmltodict.unparse(allalexaData, pretty=True)
#urlinfo = obj.urlinfo("www.pageturnpro.com")
#allalexaData = obj.urlinfo('http://www.pageturnpro.com/aboutus.aspx')
output = analyze('https://www.foodcourier.com',
'https://www.foodcourier.com/sitemap.xml')
pageError = []
for keys, song in output.items():
#for datain in song:
if type(song) == type([]):
for datain in song:
pageError.append(datain)
return render(
request, 'product/index.html', {
'domains': domain,
'alexa': data_tojson["ALEXA"]["SD"][1],
'pageError': pageError
})
def main(args=None):
if not args:
module_path = os.path.dirname(inspect.getfile(analyze))
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument(
'site', help='URL of the site you are wanting to analyze.')
arg_parser.add_argument(
'-s',
'--sitemap',
help='URL of the sitemap to seed the crawler with.')
arg_parser.add_argument('-f',
'--output-format',
help='Output format.',
choices=[
'json',
'html',
],
default='json')
args = arg_parser.parse_args()
output = analyze(args.site, args.sitemap)
if args.output_format == 'html':
from jinja2 import Environment
from jinja2 import FileSystemLoader
env = Environment(loader=FileSystemLoader(
os.path.join(module_path, 'templates')))
template = env.get_template('index.html')
output_from_parsed_template = template.render(result=output)
print(output_from_parsed_template)
elif args.output_format == 'json':
print(json.dumps(output, indent=4, separators=(',', ': ')))
else:
exit(1)
from seoanalyzer import analyze
from datetime import date
import json
import csv
# Requisição API SEO / Formatação JSON
output = analyze('https://santander.com.br/', 'https://www.santander.com.br/sitemap.xml')
output_to_json = json.dumps(output)
formated_output = json.loads(output_to_json)
indice_csv = formated_output['pages']
# Abre arquivo CSV para leitura
myFile = open('base.csv', 'a', newline='')
# Criando var a ser lida no CSV
csvwriter = csv.writer(myFile)
# Correndo o Json, e ajustes na base bruta
count = 0
for num, out in enumerate(indice_csv):
indice_csv[num]['Data'] = date.today()
indice_csv[num]['url'] = indice_csv[num]['url'].replace('http://www.', 'https://')
if count == 0:
header = out.keys()
#csvwriter.writerow(header)
count += 1
csvwriter.writerow(out.values())
myFile.close()
#! /usr/bin/env python3 # https://www.searchenginejournal.com/seo-tasks-automate-with-python/351050/ # https://github.com/sethblack/python-seo-analyzer/ from seoanalyzer import analyze # output = analyze(site, sitemap) siteA = "https://www.google.com/" analysisA = analyze(siteA) print(analysisA)
from seoanalyzer import analyze
output = analyze("https://google.co.in")
print(output)
'json',
'html',
],
default='json')
arg_parser.add_argument('-d',
'--disk',
help='save to disk',
choices=[
'y',
'n',
],
default='y')
args = arg_parser.parse_args()
output = analyze(args.site, args.sitemap)
if args.output_format == 'html':
from jinja2 import Environment
from jinja2 import FileSystemLoader
env = Environment(
loader=FileSystemLoader(os.path.join(module_path, 'templates')))
template = env.get_template('index.html')
output_from_parsed_template = template.render(result=output)
if args.disk == 'y':
with open("test.html", "w", encoding='utf-8') as text_file:
text_file.write(output_from_parsed_template)
else:
print(output_from_parsed_template)
elif args.output_format == 'json':
def test_print_output():
output = analyze('https://www.sethserver.com/tests/utf8.html')
assert False
def seo_analyser(url, sitemap):
output = analyze(url, sitemap)
print(output)