def scrape_article_name(article_id):
article = db.get_article(article_id)
if article == None:
print('There is no article with that ID. article NOT found.\n')
else:
print()
display_single_article(article, str(article.ArticleID))
article_choice = btc.read_int_ranged(
'1 to rescrape title, 2 to leave as is: ',
min_value=1,
max_value=2)
if article_choice == 1:
try:
new_article_news_item = na.get_article_from_url(article.link)
new_title = new_article_news_item.title
print('''
New title: {0}
Old title: {1}'''.format(new_title, article.name))
except:
new_title = 'Title scrape failed'
title_choice = btc.read_int_ranged(
'1 to replace title, 2 to keep original title: ',
min_value=1,
max_value=2)
if title_choice == 1:
db.update_article_name(article_id, new_title)
elif title_choice == 2:
print('article update cancelled')
elif article_choice == 2:
print('article update cancelled')
def csv_item_to_article(csv_list_item):
new_article_news_item = na.get_article_from_url(csv_list_item[0])
new_article_link = new_article_news_item.url
new_article_title = new_article_news_item.title
print(new_article_title)
new_article_category = get_category_id(csv_list_item[1])
new_article_datetime = parse(csv_list_item[2])
new_article_date = new_article_datetime.date()
article_from_csv = Article(name=new_article_title,
link=new_article_link,
category=new_article_category,
date=new_article_date,
description='Not specified',
author='Not specified',
publication='Not specified')
return article_from_csv
def update_article_name(article_id):
article = db.get_article(article_id)
if article == None:
print("There is no article with that ID. article NOT found.\n")
else:
print()
display_single_article(article, str(article.ArticleID))
article_choice = btc.read_int_ranged(
'1 to edit article title, 2 to leave as is: ',
min_value=1,
max_value=2)
if article_choice == 1:
try:
newsItem1 = na.get_article_from_url(article.link)
updated_title = newsItem1.title
except Exception as e:
print('Scrape failed because of {0}'.format(e))
updated_title = 'Invalid'
print('Rescraped title: {0}'.format(updated_title))
title_choice = btc.read_int_ranged(
'1 - existing title, 2 - scraped title, 3 - manual input: ', 1,
3)
if title_choice == 1:
print('Title update cancelled, article title unchanged.')
return
elif title_choice == 2:
db.update_article_name(article_id, updated_title)
print('Title update complete. Return to main menu.')
elif title_choice == 3:
new_title = btc.read_text('Enter new title or . to cancel: ')
if new_title != '.':
db.update_article_name(article_id, new_title)
else:
print('Edit cancelled, return to main menu')
return
else:
print('Edit cancelled, article title unchanged')
def from_newspaper(link):
'''
Adds an article from the newspaper module after downloading it
'''
for i in tqdm.tqdm(range(1)):
try:
newNewsItem = na.get_article_from_url(link)
except:
print('Article download failed, invalid URL')
print('Returning to main menu')
return
print(newNewsItem)
try:
name = newNewsItem.title #get the title for the article
except Exception as e:
print(e)
name = btc.read_text('Please enter title: ')
#get article author
try:
author = ' '.join(newNewsItem.authors)
#get article publication
except Exception as e:
print(e)
author = btc.read_text('Please enter author: ')
try:
#works for most websites, but not Sudan Tribune
publication = newNewsItem.meta_data['og']['site_name']
except Exception as e:
print(e)
publication = btc.read_text('Please enter publication: ')
try:
year = newNewsItem.publish_date.year
month = newNewsItem.publish_date.month
day = newNewsItem.publish_date.day
new_date = datetime.date(day=day, month=month, year=year)
except Exception as e:
print(e)
#use the new btc.read_date() function to simplify this
try:
new_date = btc.read_date('Enter article date MM/DD/YYYY: ')
except Exception as e:
print('invalid date', e)
try:
summary = newNewsItem.summary
except Exception as e:
print(e)
print('Summary download failed')
summary = 'Summary not found'
try:
keywords = ', '.join(newNewsItem.keywords)
except Exception as e:
print(e)
print('Keyword download failed')
keywords = 'keywords not found'
print('TITLE - {0} - AUTHOR {1}'.format(name, author))
print('DATE - {0} - PUBLICATION {1}'.format(new_date.strftime("%m/%d/%Y"),
publication))
print('KEYWORDS: ', keywords)
display_categories()
category_id = btc.read_text("Category ID: ")
category = db.get_category(category_id)
if category == None:
print('There is no category with that ID. article NOT added.\n')
return
description_choice = btc.read_text('View article description? y/n: ')
if description_choice == 'y':
print('Title: {0}'.format(name))
print('Summary: {0}'.format(summary))
print('Keywords: {0}'.format(keywords))
description = btc.read_text("Description or '.' to cancel: ")
if description == ".":
return
else:
new_article = Article(name=name,
date=new_date,
category=category,
link=link,
description=description,
author=author,
publication=publication)
display_single_article(article=new_article,
title_term=new_article.name)
confirm_article = btc.read_bool(decision="Finalize the article?",
yes='y',
no='n',
yes_option='Confirm',
no_option='Cancel')
#This is the user's last chance to decide if they want to add the article
if confirm_article == True:
db.add_article(new_article)
print(new_article.name + " was added to database.\n")
elif confirm_article == False:
print('Article add cancelled. Return to main menu.')
def rescrape(article_id, update_type):
#update_types: name and description
#We need to shorten this function, or replace it with a class
article = db.get_article(article_id)
if article == None:
print("There is no article with that ID. article NOT found.\n")
else:
print()
display_single_article(article, str(article.articleID))
article_choice = btc.read_int_ranged(
'1 to edit article {0}, 2 to leave as is: '.format(update_type),
min_value=1,
max_value=2)
if article_choice == 1:
try:
newsItem1 = na.get_article_from_url(article.link)
except Exception as e:
print(e)
if update_type == 'name':
try:
updated_title = newsItem1.title
print('Rescraped title: {0}'.format(updated_title))
except Exception as e:
print(e)
updated_title = 'Invalid'
title_choice = btc.read_int_ranged(
'1 - existing title, 2 - scraped title, 3 - manual input: ',
1, 3)
if title_choice == 1:
print('Title update cancelled, article title unchanged.')
return
elif title_choice == 2:
new_value = updated_title
elif title_choice == 3:
new_value = btc.read_text(
'Enter new title or . to cancel: ')
if new_value == '.':
print('Edit cancelled, return to main menu')
return
elif update_type == 'description':
description_choice = btc.read_text(
'View article summary? y/n: ')
if description_choice == 'y':
try:
article_summary = newsItem1.summary
except Exception as e:
print(e)
article_summary = 'Not found'
print(article_summary)
new_value = btc.read_text(
'Enter new description or "." to cancel: ')
if new_value == '.':
print(
'Description update cancelled, return to main menu'
)
return
db.update_article(article_id=article_id,
new_value=new_value,
update_type=update_type)
print('Article {0} updated.\n'.format(update_type))
else:
print('Edit cancelled, article description unchanged')