def create_link_preview(page: MetadataParser, page_meta: dict,
url: str) -> Optional[str]:
"""
Create a preview bookmark card from a URL.
:param MetadataParser page: Page object create from URL to be parsed.
:param dict page_meta: Page metadata parsed from the head of the target URL.
:param str url: URL of the linked third-party post/article.
:returns: Optional[str]
"""
try:
title, description, page_type = parse_scraped_metadata(page_meta)
image = page.get_metadata_link("image",
allow_encoded_uri=True,
require_public_global=True)
if title is not None and description is not None:
preview = f"\n\n<b>{title}</b>\n{description}\n{url}"
if page_type:
preview += f"\n{page_type.title()}"
if image:
preview += f"\n{image}"
return preview
except Exception as e:
LOGGER.error(
f"Unexpected error while generating link preview card: {e}")
def fetch_president_articles():
from metadata_parser import MetadataParser
created = 0
updated = 0
articles_to_fetch = PresidentCandidateArticle.objects.filter(
information__isnull=True)
for article in articles_to_fetch:
page = MetadataParser(url=article.url)
title = first_or_none(page.get_metadatas('title'))
description = first_or_none(page.get_metadatas('description'))
site = first_or_none(page.get_metadatas('site_name'))
url = page.get_url_canonical()
url = url if url else article.url
image_url = page.get_metadata_link('image')
information_obj, is_created = PresidentCandidateArticleInformation.objects.update_or_create(
article=article,
defaults={
'title': title,
'description': description,
'site': site,
'url': url
})
save_image_from_url(information_obj.image, image_url)
if is_created:
created += 1
else:
updated += 1
return {'created': created, 'updated': updated}
'http://hw.libsyn.com/p/d/d/6/dd6b0db2d4858640/ARIYNBF_107_JamesGunn.mp3?sid=78edb823ad1b62ff6f329d68bbb2cc6a&l_sid=35168&l_eid=&l_mid=2952818&expiration=1334720066&hwt=7acfe1754c8dedc4f134b473894c9208'
]
for i in urls:
a = MetadataParser(url=i)
print(a.__dict__)
if 0:
url = 'http://soundcloud.com/electricyouthmusic'
a = MetadataParser(url=url)
print(a.__dict__)
if 0:
url = 'http://agrrrdog.blogspot.in/2016/06/remote-detection-of-users-av-via-flash.html'
a = MetadataParser(url=url)
pprint.pprint(a.metadata)
print a.get_metadata_link('image', strategy=['og'])
print a.get_metadata_link('image', strategy=['og'])
print a.peername
if 0:
url = 'https://twitter.com/gaussian36/status/810919575172825088'
a = MetadataParser(url=url, search_head_only=False)
pprint.pprint(a.metadata)
print a.peername
if 1:
url = 'http://nyp.st/2ikSU6N'
a = MetadataParser(url=url, search_head_only=False)
pprint.pprint(a.metadata)
print a.peername
def social_card_image(page_url):
parser = MetadataParser(url=page_url, search_head_only=True)
link = parser.get_metadata_link('image', strategy=['og'])
return link
'http://hw.libsyn.com/p/d/d/6/dd6b0db2d4858640/ARIYNBF_107_JamesGunn.mp3?sid=78edb823ad1b62ff6f329d68bbb2cc6a&l_sid=35168&l_eid=&l_mid=2952818&expiration=1334720066&hwt=7acfe1754c8dedc4f134b473894c9208'
]
for i in urls:
a = MetadataParser(url=i)
print(a.__dict__)
if 0:
url = 'http://soundcloud.com/electricyouthmusic'
a = MetadataParser(url=url)
print(a.__dict__)
if 0:
url = 'http://agrrrdog.blogspot.in/2016/06/remote-detection-of-users-av-via-flash.html'
a = MetadataParser(url=url)
pprint.pprint(a.metadata)
print a.get_metadata_link('image', strategy=['og'])
print a.get_metadata_link('image', strategy=['og'])
print a.peername
if 0:
url = 'https://twitter.com/gaussian36/status/810919575172825088'
a = MetadataParser(url=url, search_head_only=False)
pprint.pprint(a.metadata)
print a.peername
if 1:
url = 'http://nyp.st/2ikSU6N'
a = MetadataParser(url=url, search_head_only=False)
pprint.pprint(a.metadata)
print a.peername
