def get_link_embed_data(
url: str,
maxwidth: Optional[int] = 640,
maxheight: Optional[int] = 480) -> Optional[Dict[str, Any]]:
if not is_link(url):
return None
if not valid_content_type(url):
return None
# We are using two different mechanisms to get the embed data
# 1. Use OEmbed data, if found, for photo and video "type" sites
# 2. Otherwise, use a combination of Open Graph tags and Meta tags
data = get_oembed_data(url, maxwidth=maxwidth, maxheight=maxheight) or {}
if data.get('oembed'):
return data
response = requests.get(mark_sanitized(url),
stream=True,
headers=HEADERS,
timeout=TIMEOUT)
if response.ok:
og_data = OpenGraphParser(response.text).extract_data()
for key in ['title', 'description', 'image']:
if not data.get(key) and og_data.get(key):
data[key] = og_data[key]
generic_data = GenericParser(response.text).extract_data() or {}
for key in ['title', 'description', 'image']:
if not data.get(key) and generic_data.get(key):
data[key] = generic_data[key]
return data
def get_link_embed_data(url: str,
maxwidth: int = 640,
maxheight: int = 480) -> Optional[Dict[str, Any]]:
if not is_link(url):
return None
if not valid_content_type(url):
return None
# We are using two different mechanisms to get the embed data
# 1. Use OEmbed data, if found, for photo and video "type" sites
# 2. Otherwise, use a combination of Open Graph tags and Meta tags
data = get_oembed_data(url, maxwidth=maxwidth, maxheight=maxheight) or {}
if data.get("oembed"):
return data
response = PreviewSession().get(mark_sanitized(url), stream=True)
if response.ok:
og_data = OpenGraphParser(
response.content,
response.headers.get("Content-Type")).extract_data()
for key in ["title", "description", "image"]:
if not data.get(key) and og_data.get(key):
data[key] = og_data[key]
generic_data = (GenericParser(
response.content,
response.headers.get("Content-Type")).extract_data() or {})
for key in ["title", "description", "image"]:
if not data.get(key) and generic_data.get(key):
data[key] = generic_data[key]
return data