Get link preview in python
Gathering data from:
- OpenGraph meta tags
- TwitterCard meta tags
- Microdata meta tags
- JSON-LD meta tags
- HTML Generic tags (
h1,p,img) - URL readable parts
pip install linkpreview
from linkpreview import link_preview
url = "http://localhost"
content = """
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width">
<!-- ... --->
<title>a title</title>
</head>
<body>
<!-- ... --->
</body>
</html>
"""
preview = link_preview(url, content)
print("title:", preview.title)
print("description:", preview.description)
print("image:", preview.image)
print("force_title:", preview.force_title)
print("absolute_image:", preview.absolute_image)
print("site_name:", preview.site_name)
print("favicon:", preview.favicon)
print("absolute_favicon:", preview.absolute_favicon)from linkpreview import link_preview
preview = link_preview("http://github.com/")
print("title:", preview.title)
print("description:", preview.description)
print("image:", preview.image)
print("force_title:", preview.force_title)
print("absolute_image:", preview.absolute_image)
print("site_name:", preview.site_name)
print("favicon:", preview.favicon)
print("absolute_favicon:", preview.absolute_favicon)Very recommended for better performance.
Install the lxml and use it like this:
from linkpreview import link_preview
preview = link_preview("http://github.com/", parser="lxml")
print("title:", preview.title)
print("description:", preview.description)
print("image:", preview.image)
print("force_title:", preview.force_title)
print("absolute_image:", preview.absolute_image)
print("site_name:", preview.site_name)
print("favicon:", preview.favicon)
print("absolute_favicon:", preview.absolute_favicon)from linkpreview import Link, LinkPreview, LinkGrabber
url = "http://github.com"
grabber = LinkGrabber(
initial_timeout=20,
maxsize=1048576,
receive_timeout=10,
chunk_size=1024,
)
content, url = grabber.get_content(url)
link = Link(url, content)
preview = LinkPreview(link, parser="lxml")
print("title:", preview.title)
print("description:", preview.description)
print("image:", preview.image)
print("force_title:", preview.force_title)
print("absolute_image:", preview.absolute_image)
print("site_name:", preview.site_name)
print("favicon:", preview.favicon)
print("absolute_favicon:", preview.absolute_favicon)Extend default headers:
content, url = grabber.get_content(url, headers={'user-agent': 'Twitterbot'})Ignore default headers:
content, url = grabber.get_content(
url,
headers={'user-agent': 'Twitterbot', 'accept': '*/*'},
replace_headers=True,
)Use preset headers:
content, url = grabber.get_content( url, headers='googlebot')Available presets:
firefox,
chrome,
googlebot,
twitterbot,
telegrambot,
imessagebot
If you already have parsed BeautifulSoup object:
from bs4 import BeautifulSoup
from linkpreview import Link, LinkPreview
url = "http://example.com"
content = "<h1>Hello</h1>"
soup = BeautifulSoup(content, "html.parser")
link = Link(url, content)
preview = LinkPreview(link, soup=soup)
print("title:", preview.title)