def saveReqToFile(req, fileName):
printTab("Saving %s to %s" % (req.url, fileName))
setupTestData()
#Save to file the content of request...
theFile = getFilePath(fileName)
with open(theFile, 'wb') as f:
# Is possible to do f.write(theFile.content)
# However, this is the recommend way for (possible) large responses
# Write in chunks... I decide in 512.
# http://stackoverflow.com/questions/13137817/how-to-download-image-using-requests
for chunk in req.iter_content(512):
f.write(chunk)
articles.append(createArticle(
title=entry.title,
description=entry.description,
source=source,
date=entry.published
))
printExplain("To save several objects, use the batcher")
batcher = ParseBatcher()
batcher.batch_save(articles)
print "Our news sources:"
for source in sources.values():
printTab(source.title)
print "The news from ", sources.values()[0].title
for new in Article.Query.filter(source=sources.values()[0]):
printSubTitle(new.title)
print new.description
printTitle("Conclusion")
print """
Parse.com provide a easy way of store/query data, with not admin skills.
Is not a replacemente for a proper Sql database (like postgresql or sql server)
but provide a flexible data model apropiated for quick development and/or scalable
acces to data, where the data must be denormalized anyway..
"""
The first, is a URL link to a main topic, then the actual news.
The other is just the new.
"""
# Set recursive=False to get only the first level of tags. If is True,
# It will get all the tags below the tree, complicating the logic to
# separate the 2 kinds of news...
for event in tableEvents:
ulNew = event.find_all("tr")[2].td.find_all('ul', recursive=False)
for ul in ulNew:
for li in ul.find_all('li', recursive=False):
subUls = li.find_all('ul')
# Is a headline + new(s)?
if len(subUls):
for subUl in subUls:
processNews(subUl.find_all('li'))
else:
# Is a normal headline
processNews([li])
for category in sorted(news):
headlines = news[category]
printSubTitle(category.encode('ascii', 'ignore'))
for headline in headlines:
printTab(headline.encode('ascii', 'ignore'))
print