Created
November 20, 2019 21:38
-
-
Save dunnousername/a7d27c73b574443a884c4504d739f023 to your computer and use it in GitHub Desktop.
schema.org checker I made in like 5 minutes. Useful for scraping for pages that support schema.org.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python3 | |
# usage: schemachecker.py urls... | |
# requires: python 3, beautiful soup 4, requests library | |
from bs4 import BeautifulSoup | |
import requests | |
import sys | |
def checkUrl(url): | |
r = requests.get(url, headers={'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:10.0) Gecko/20100101 Firefox/10.0'}) | |
soup = BeautifulSoup(r.text, 'html.parser') | |
types = set() | |
for item in soup.find_all(itemtype=True): | |
types.add(item.get('itemtype')) | |
for t in types: | |
if t: | |
print('- contains a "{}" schema'.format(t)) | |
for url in sys.argv[1:]: | |
print(url) | |
checkUrl(url) | |
""" | |
> python .\schemachecker.py https://google.com https://www.allrecipes.com/recipe/95294/chewy-caramel/ | |
https://google.com | |
- contains a "http://schema.org/WebPage" schema | |
https://www.allrecipes.com/recipe/95294/chewy-caramel/ | |
- contains a "http://schema.org/Recipe" schema | |
- contains a "http://schema.org/BreadcrumbList" schema | |
- contains a "http://schema.org/ListItem" schema | |
- contains a "http://schema.org/Rating" schema | |
- contains a "http://schema.org/Review" schema | |
- contains a "http://schema.org/AggregateRating" schema | |
- contains a "http://schema.org/NutritionInformation" schema | |
""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Tested with Anaconda on Windows 10.