def test_sort_articles(self):
sample_article_0 = CMR_Article()
sample_article_0.title = "ABC, Parker’s Piece, 7 July 2017"
sample_article_0.url = "http://example_url_0.com"
sample_article_1 = CMR_Article()
sample_article_1.title = "Lee Hull, Corner House, Cambridge, 4 June 2017"
sample_article_1.url = "http://example_url_1.com"
sample_article_1.index_text = "Lee Hull, 4th June 2017"
sample_article_1.category = CMR_Index_Categories.live
sample_article_2 = CMR_Article()
sample_article_2.title = "z"
sample_article_2.url = "http://example_url_0.com"
sample_article_2.index_text = "z"
sample_article_2.category = CMR_Index_Categories.extra
sample_article_3 = CMR_Article()
sample_article_3.title = "z"
sample_article_3.url = "http://example_url_0.com"
sample_article_3.index_text = "w"
sample_article_3.category = CMR_Index_Categories.extra
articles = [sample_article_0, sample_article_1,
sample_article_2, sample_article_3]
sort_articles(articles)
self.assertEqual(articles[0].title,'z')
self.assertEqual(articles[0].index_text,'w')
self.assertEqual(articles[1].title,'z')
self.assertEqual(articles[1].index_text,'z')
self.assertEqual(articles[2].title,"Lee Hull, Corner House, Cambridge, 4 June 2017")
self.assertEqual(articles[3].title,"ABC, Parker’s Piece, 7 July 2017")
def example_save_index_html():
sample_article_0 = CMR_Article()
sample_article_0.title = "ABC, Parker’s Piece, 7 July 2017"
sample_article_0.url = "http://example_url_0.com"
sample_article_1 = CMR_Article()
sample_article_1.title = "Lee Hull, Corner House, Cambridge, 4 June 2017"
sample_article_1.url = "http://example_url_1.com"
sample_article_1.index_text = "Lee Hull, 4th June 2017"
sample_article_1.category = CMR_Index_Categories.live
articles = [sample_article_0, sample_article_1]
print("before filling in missing details:")
for article in articles:
print("----")
article.print_article_details()
fill_in_missing_data_interactive(articles)
save_index_html(articles, "test.html")
articles = get_all_cmr_articles()
fill_in_missing_data_interactive(articles)
save_index_html(articles, "test.html")
def example_CMR_Article():
#Create a CMR_Article object
print("------- create an article with no data in it")
my_article = CMR_Article()
# print out its contents
my_article.print_article_details()
# fill in some details
print("------- set a title for the article")
my_article.title = "Ed Sheeran, Wembley Stadium, July 1st 2017"
# print out its contents
my_article.print_article_details()
# fill in more details
print("------- set other data for the article")
my_article.url = "http://made_up_address.html"
my_article.index_text = "Ed Sheeran"
my_article.category = CMR_Index_Categories.live
# print out its contents
my_article.print_article_details()
# change in some details
print("------- set a title for the article")
my_article.title = "Ed Sheeran, Wembley Stadium, August 11th 2017"
# print out its contents
my_article.print_article_details()
def setup_articles():
sample_article_0 = CMR_Article()
sample_article_0.title = "ABC, Parker’s Piece, 7 month-year"
sample_article_0.url = "http://example_url_0.com"
sample_article_1 = CMR_Article()
sample_article_1.title = "Lee Hull, Corner House, Cambridge, 4 June 2017"
sample_article_1.url = "http://example_url_1.com"
sample_article_1.index_text = "Lee Hull, 4th Junish 2017"
sample_article_1.category = CMR_Index_Categories.live
sample_article_2 = CMR_Article()
sample_article_2.title = "no idea, what this is, 1 month-year"
sample_article_2.url = "http://example_url_2.com"
articles = [sample_article_0, sample_article_1, sample_article_2]
fill_in_missing_data(articles,
_get_missing_index_text_test,
_get_missing_category_test,
_confirm_test,
_confirm_test,
_confirm_test)
return articles
def get_index_anchors(soup, tag, category):
#set up an empty list to hold data for each link
articles_found = []
#the headings we're interested in all have class = given tag
#ask soup for a list of such headings
my_div = soup.find("div", { "class" : tag })
anchors = my_div.findAll('a')
#iterate over these anchors compiling data into result_data
for anchor in anchors:
#for each one get the text the human sees and the link url
this_index_text = str(anchor.contents[0])
this_url = str(anchor["href"])
# build a CMR_Article
this_article = CMR_Article()
this_article.index_text = this_index_text
this_article.url = this_url
this_article.category = category
articles_found.append(this_article)
#pass the results back to the calling code
return articles_found