def create_rss_object(all_titles_with_s3, pod):
items_list = []
for title in all_titles_with_s3:
id = title["data-media-id"]
guid = f"https://{pod.bucket_name}.s3.amazonaws.com/{id}.mp3"
url = guid
item = Item(
title=title["data-asset-title"],
link=url,
description=title["data-title-description"],
author="France Culture",
guid=Guid(guid),
pubDate=datetime.datetime.fromtimestamp(
int(title["data-asset-created-date"])),
)
items_list.append(item)
feed = Feed(
title=pod.podcast,
link="https://www.franceculture.fr/emissions/" + pod.podcast,
image=Image(pod.podcast_pic_url, pod.podcast, pod.podcast_url)
if pod.podcast_pic_url is not None else None,
description=pod.podcast,
language="en-US",
lastBuildDate=datetime.datetime.now(),
items=items_list,
)
return feed
def pop_blog(f, blog_dir, post_dict, post_template, main_template):
"""populates an html page from an org blog post
Parameters
----------
f : str
basename for org file
blog_dir : str
location where org blog posts are located
post_dict : dict
dictionary of posts mapping titles to urls
post_template : jinja2 Template instance
template containing content for blog post
main_template : jinja2 Template instnace
template for adding style to blog post
Returns
-------
tuple
containing updated post_dict and item to add to rss feed
"""
# prep inputs
bn, ext = os.path.splitext(f)
comp = bn.split("-")
date = "-".join(comp[:3])
title = " ".join(comp[3:])
full_title = "%s %s" % (date, title)
full_path = os.path.join(blog_dir, f)
html_f = os.path.join("posts", bn + ".html")
url = "https://lbybee.github.io/%s" % html_f
# build html
cmd = "pandoc -r org -t html --mathjax %s -o /dev/stdout"
html = spbash(cmd % full_path)
html = post_template.render(date=date, pandoc_html=html)
html = main_template.render(title=title, content_html=html)
with open(html_f, "w") as fd:
fd.write(html)
# add to rss feed
item = Item(title=full_title,
link=url,
author="Leland Bybee",
description=full_title,
guid=Guid(url),
pubDate=parse(date))
# update content dict
post_dict[full_title] = url
return post_dict, item
def build_item(post: Post, base_url: Url, base_image_url: Url) -> Item:
link = post.link(base_url)
return Item(
title=post.title,
link=link,
description=post.metadata.description,
author=post.metadata.author,
guid=Guid(link),
pubDate=post.metadata.date,
categories=[Category(tag) for tag in post.metadata.tags],
enclosure=PostWrapper(post, base_image_url),
)
def proposals(space):
# Get the proposal from the space
graphql_query = """
{
proposals(
orderBy: "created",
orderDirection: desc,
where:{space:"%s", state:"active"}
) {
id
title
body
created
author
state
}
}
""" % space
r = requests.post('%s/graphql' % SNAPSHOT_API_ENDPOINT,
json={'query': graphql_query})
# Success response
if r.ok:
# Build list of items
items = []
for proposal in r.json()['data']['proposals']:
items.append(
Item(
title=proposal['title'],
link='%s/#/%s/proposal/%s' %
(SNAPSHOT_BASE_URL, space, proposal['id']),
description=proposal['body'],
author=proposal['author'],
guid=Guid(proposal['id'], False),
pubDate=datetime.fromtimestamp(int(proposal['created'])),
))
feed = Feed(title='%s Proposals' % space,
link='%s/api/v1/spaces/%s/proposals' %
(RSS_FEED_BASE_URL, space),
description="Proposals for %s" % space,
language='en-US',
lastBuildDate=datetime.now(),
items=items)
return feed.rss()
else:
return jsonify({'code': r.status_code, 'text': r.text})
def generate_rss_feed(records):
now_utc = datetime.now(timezone.utc)
items = []
for record in available_records_generator(records):
description = f"""
<h1>Vaccine availble</h1>
<table>
<tr>
<th>Provider</th>
<th>Store Name</th>
<th>Store Address</th>
<th>Store City</th>
<th>Appointment Link</th>
</tr>
<tr>
<td>{record.provider}</td>
<td>{record.store_name}</td>
<td>{record.store_address}</td>
<td>{record.store_city}</td>
<td><a href="{record.link}">{record.link}</a></td>
</tr>
</table>
"""
item = Item(
title="Vaccine Available",
description=description,
guid=Guid(
f"{record.store_name}{record.store_address}{record.store_city}{str(now_utc.date())}",
isPermaLink=False,
),
pubDate=now_utc,
)
items.append(item)
feed = Feed(
title="Covid Vaccine Finder Updates",
link="https://kirkhansen.github.io/covid-vaccine-finder/",
description=
"Feed produces new records when available vaccine is detected.",
language="en-US",
lastBuildDate=now_utc,
items=items,
)
return feed
def rss_view(id):
# Get all searchs from user
search = Search.query.get(id)
# Fix prices
min_price = search.min_price
if min_price == 0:
min_price = ''
max_price = search.max_price
if max_price == 0:
max_price = ''
# Get Data
cookies = {
'searchLat': str(search.lat),
'searchLng': str(search.lng),
'content': str(search.name),
'hideCookieMessage': 'true',
'userHasLogged': '%7B%22hasLogged%22%3Afalse%2C%22times%22%3A1%7D '
}
urlSearch = f'https://es.wallapop.com/rest/items?dist={search.distance}&kws={search.name}&lat={search.lat}&lng={search.lng}&maxPrice={max_price}&minPrice={min_price}'
results = requests.get(urlSearch, cookies=cookies).json()['items']
# Generate RSS
items = []
for result in results:
items.append(
Item(
title=
f"{result['title']} - {result['salePrice']}{result['currency']['symbol']}",
link=f"https://es.wallapop.com/item/{result['url']}",
description=result['description'],
author=result['sellerUser']['microName'],
guid=Guid(result['itemId']),
pubDate=datetime.utcfromtimestamp(
int(str(result['publishDate'])[:-3]))))
lastBuildDate = datetime.now()
if results:
lastBuildDate = datetime.utcfromtimestamp(
int(str(results[0]['publishDate'])[:-3]))
feed = Feed(
title=f"{search.name} - Wallaviso RSS",
link="http://www.wallaviso.com",
description=
"Se el primero en Wallapop. Programa tus busquedas y recibe una notificacion al instante.",
language="es-ES",
lastBuildDate=lastBuildDate,
items=items)
return feed.rss()
def getArticleSummary(article_link, headline):
r2 = requests.get(article_link)
soup2 = BeautifulSoup(r2.text, features="html.parser")
i = 1
publication_date = soup2.find('time')['datetime']
data2 = soup2.findAll('p')[i]
#For some reason the page likes to have random paragraphs which are empty?
#So we set i=1 and increase it if there is more empty or near empty strings detected ie building names
while (len(data2.text) < 30):
i = i + 1
data2 = soup2.findAll('p')[i]
article_pub_date = datetime.datetime.strptime(publication_date,
"%Y-%m-%d %H:%M:%S")
#append to articles_list in order to print as RSS compatible XML
articles_list.append(
Item(title=headline,
link=article_link,
description=data2.text,
guid=Guid(article_link),
pubDate=datetime.datetime(article_pub_date.year,
article_pub_date.month,
article_pub_date.day,
article_pub_date.hour,
article_pub_date.minute)))
def get_xml(self: Serializer, response: Response) -> Tuple[str, int]:
"""
Serialize the provided response data into RSS, version 2.0.
Parameters
----------
response : Response
The search response data to be serialized.
Returns
-------
data : str
The serialized XML results.
status
The HTTP status code for the operation.
"""
# Get the archive info from the first hit. Is this OK?
archive = response.hits[0]["primary_classification"]["archive"]
archive_id = archive["id"]
archive_name = archive["name"]
feed = Feed(
title=f"{archive_id} updates on arXiv.org",
link="http://arxiv.org/",
description=f"{archive_name} ({archive_id}) updates on the arXiv.org e-print archive",
language="en-us",
pubDate=datetime.now(),
lastBuildDate=datetime.now(),
managingEditor="*****@*****.**"
)
# Remove two elements added by the Rfeed package
feed.generator = None
feed.docs = None
# Add extensions that will show up as attributes of the rss element
feed.extensions.append(Content())
feed.extensions.append(Taxonomy())
feed.extensions.append(Syndication())
feed.extensions.append(Admin())
feed.image = Image(url="http://arxiv.org/icons/sfx.gif",
title="arXiv.org", link="http://arxiv.org")
# Add each search result "hit" to the feed
for hit in response:
# Add links for each author and the abstract to the description element
description = "<p>Authors: "
first = True
for author in hit['authors']:
if first:
first = False
else:
description += ", "
name = f"{author['last_name']},+{author['initials'].replace(' ', '+')}"
description += f"<a href='http://arxiv.org/search/?query={name}&searchtype=author'>"
description += f"{author['full_name']}</a>"
description += f"</p><p>{hit['abstract']}</p>"
# Create the item element for the "hit"
item = Item(
title=hit['title'],
link=url_for("abs_by_id", paper_id=hit['paper_id']),
# link=f"http://arxiv.org/abs/{hit['paper_id']}",
description=description,
guid=Guid(f"oai:arXiv.org:{hit['paper_id']}", isPermaLink=False)
)
feed.items.append(item)
# Print and return the feed content
data = feed.rss()
status_code = status.HTTP_200_OK
return data, status_code