def process(url):
"""
Fetches news items from the rss url and parses them.
Returns a list of NewsStory-s.
"""
feed = feedparser.parse(url)
entries = feed.entries
ret = []
for entry in entries:
guid = entry.guid
title = translate_html(entry.title)
link = entry.link
description = translate_html(entry.description)
pubdate = translate_html(entry.published)
try:
pubdate = datetime.strptime(pubdate, "%a, %d %b %Y %H:%M:%S %Z")
pubdate.replace(tzinfo=pytz.timezone("GMT"))
# pubdate = pubdate.astimezone(pytz.timezone('EST'))
# pubdate.replace(tzinfo=None)
except ValueError:
pubdate = datetime.strptime(pubdate, "%a, %d %b %Y %H:%M:%S %z")
newsStory = NewsStory(guid, title, description, link, pubdate)
ret.append(newsStory)
return ret
def process(url):
"""
Fetches news items from the rss url and parses them.
Returns a list of NewsStory-s.
"""
if hasattr(ssl, '_create_unverified_context'):
ssl._create_default_https_context = ssl._create_unverified_context
feed = feedparser.parse(url)
entries = feed.entries
ret = []
for entry in entries:
guid = entry.guid
title = translate_html(entry.title)
published = translate_html(entry.published)
link = entry.link
summary = translate_html(entry.summary)
newsStory = NewsStory(guid, title, published, summary, link)
ret.append(newsStory)
return ret
def process(url):
"""
Fetches news items from the rss url and parses them.
Returns a list of NewsStory-s.
"""
feed = feedparser.parse(url)
entries = feed.entries
ret = []
for entry in entries:
guid = entry.guid
title = translate_html(entry.title)
link = entry.link
summary = translate_html(entry.summary)
try:
subject = translate_html(entry.tags[0]['term'])
except AttributeError:
subject = ""
newsStory = NewsStory(guid, title, subject, summary, link)
ret.append(newsStory)
return ret
def process(url):
"""
Fetches news items from the rss url and parses them.
Returns a list of NewsStory-s.
"""
feed = feedparser.parse(url)
entries = feed.entries
ret = []
for entry in entries:
guid = entry.guid
title = translate_html(entry.title)
link = entry.link
summary = translate_html(entry.summary)
try:
subject = translate_html(entry.tags[0]['term'])
except AttributeError:
subject = ""
newsStory = NewsStory(guid, title, subject, summary, link)
ret.append(newsStory)
return ret
def process(url):
"""
Fetches news items from the rss url and parses them.
Returns a list of NewsStory-s.
"""
feed = feedparser.parse(url)
entries = feed.entries
ret = []
for entry in entries:
guid = entry.guid
title = translate_html(entry.title)
link = entry.link
# Had to add error handling because yahoo news doesn't give
# descriptions anymore
try:
description = translate_html(entry.description)
except AttributeError:
description = ''
pubdate = translate_html(entry.published)
try:
pubdate = datetime.strptime(pubdate, "%a, %d %b %Y %H:%M:%S %Z")
pubdate.replace(tzinfo=pytz.timezone("GMT"))
# pubdate = pubdate.astimezone(pytz.timezone('EST'))
# pubdate.replace(tzinfo=None)
except ValueError:
#added error handling because date format in google page changed
try:
pubdate = datetime.strptime(pubdate, "%a, %d %b %Y %H:%M:%S %z")
except ValueError: #added new date-time format that google outputs
pubdate = datetime.strptime(pubdate, "%Y-%m-%dT%H:%M:%S%z")
newsStory = NewsStory(guid, title, description, link, pubdate)
ret.append(newsStory)
return ret
def fprocess(entry):
guid = entry.guid
title = entry.title.split(" - ")[0]
published = entry.published
source = entry.source.title
link = entry.link
web_content = readability.Document(requests.get(link).text)
summary = translate_html(web_content.summary())
newsStory = NewsStory(guid, title, summary, published, source, link)
return newsStory
