Skip to content

Fix SEO extraction order-independent by replacing regex with BeautifulSoup #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
e9srawat wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

Fix SEO extraction order-independent by replacing regex with BeautifulSoup #9

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 50 additions & 20 deletions seo/scanner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
import re
from urllib.parse import urlparse
from xml.etree import ElementTree

from bs4 import BeautifulSoup
import requests
from django.utils import timezone

Expand All @@ -24,19 +24,32 @@
# SEO extraction patterns
# ---------------------------------------------------------------------------

SEO_PATTERNS = {
"title": r"<title>(.*?)</title>",
"meta_description": r'name="description"\s+content="([^"]*)"',
"canonical": r'rel="canonical"\s+href="([^"]*)"',
"og_url": r'property="og:url"\s+content="([^"]*)"',
"og_site_name": r'property="og:site_name"\s+content="([^"]*)"',
"og_title": r'property="og:title"\s+content="([^"]*)"',
"og_description": r'property="og:description"\s+content="([^"]*)"',
"og_image": r'property="og:image"\s+content="([^"]*)"',
"twitter_card": r'name="twitter:card"\s+content="([^"]*)"',
"twitter_title": r'name="twitter:title"\s+content="([^"]*)"',
"twitter_description": r'name="twitter:description"\s+content="([^"]*)"',
"twitter_image": r'name="twitter:image"\s+content="([^"]*)"',
# SEO_PATTERNS = {
# "title": r"<title>(.*?)</title>",
# "meta_description": r'name="description"\s+content="([^"]*)"',
# "canonical": r'rel="canonical"\s+href="([^"]*)"',
# "og_url": r'property="og:url"\s+content="([^"]*)"',
# "og_site_name": r'property="og:site_name"\s+content="([^"]*)"',
# "og_title": r'property="og:title"\s+content="([^"]*)"',
# "og_description": r'property="og:description"\s+content="([^"]*)"',
# "og_image": r'property="og:image"\s+content="([^"]*)"',
# "twitter_card": r'name="twitter:card"\s+content="([^"]*)"',
# "twitter_title": r'name="twitter:title"\s+content="([^"]*)"',
# "twitter_description": r'name="twitter:description"\s+content="([^"]*)"',
# "twitter_image": r'name="twitter:image"\s+content="([^"]*)"',
# }

META_TAGS_MAP = {
"description": "meta_description",
"twitter:card": "twitter_card",
"twitter:title": "twitter_title",
"twitter:description": "twitter_description",
"twitter:image": "twitter_image",
"og:url": "og_url",
"og:site_name": "og_site_name",
"og:title": "og_title",
"og:description": "og_description",
"og:image": "og_image",
}

# Tags that must have non-empty values on every public page.
Expand All @@ -58,13 +71,30 @@
# ---------------------------------------------------------------------------


# def extract_seo(html):
# """Extract SEO tag values from rendered HTML into a dict."""
# values = {}
# for key, pattern in SEO_PATTERNS.items():
# match = re.search(pattern, html, re.DOTALL)
# values[key] = match.group(1).strip() if match else None
# return values


def extract_seo(html):
"""Extract SEO tag values from rendered HTML into a dict."""
values = {}
for key, pattern in SEO_PATTERNS.items():
match = re.search(pattern, html, re.DOTALL)
values[key] = match.group(1).strip() if match else None
return values
soup = BeautifulSoup(html, "html.parser")
data = {
"title": soup.title.string.strip() if soup.title and soup.title.string else None,
"canonical": (link := soup.find("link", rel="canonical")) and link.get("href"),
}
for tag in soup.find_all("meta"):
content = tag.get("content")
if not content:
continue
if (name := tag.get("name")) in META_TAGS_MAP:
data[META_TAGS_MAP[name]] = content
elif (name := tag.get("property")) in META_TAGS_MAP:
data[META_TAGS_MAP[name]] = content
return data


def check_seo_quality(seo):
Expand Down