def verge_listen(self, event):
currlinks, currtitles, currcategories = grabheadline.grabfront("https://www.theverge.com/")
if len(currlinks) == 0:
tk.messagebox.showerror("Error", "Failed to Retrieve Website. No Internet Connection?")
else:
self.title.pack_forget()
self.main2.pack_forget()
self.prev.pack_forget()
fpl = FrontPageList(self.currMaster, 'The Verge', currlinks, currtitles, currcategories, self.currPage)
def guardian_listen(self, event):
currlinks, currtitles, currcategories = grabheadline.grabfront('https://www.theguardian.com/international')
if len(currlinks) == 0:
tk.messagebox.showerror("Error", "Failed to Retrieve Website. No Internet Connection?")
else:
self.title.pack_forget()
self.main1.pack_forget()
self.next.pack_forget()
fpl = FrontPageList(self.currMaster, 'The Guardian', currlinks, currtitles, currcategories, self.currPage)
def huffington_listen(self, event):
currlinks, currtitles, currcategories = grabheadline.grabfront("http://huffpost.com")
if len(currlinks) == 0:
tk.messagebox.showerror("Error", "Failed to Retrieve Website. No Internet Connection?")
else:
self.title.pack_forget()
self.main2.pack_forget()
self.prev.pack_forget()
fpl = FrontPageList(self.currMaster, 'Huffington Post', currlinks, currtitles, currcategories,
self.currPage)
def latimes_listen(self, event):
currlinks, currtitles, currcategories = grabheadline.grabfront('https://latimes.com')
if len(currlinks) == 0:
tk.messagebox.showerror("Error", "Failed to Retrieve Website. No Internet Connection?")
else:
self.title.pack_forget()
self.main2.pack_forget()
self.prev.pack_forget()
fpl = FrontPageList(self.currMaster, 'Los Angeles Times', currlinks, currtitles, currcategories,
self.currPage)
def ap_listen(self, event):
currlinks, currtitles, currcategories = grabheadline.grabfront('https://apnews.com')
if len(currlinks) == 0:
tk.messagebox.showerror("Error", "Failed to Retrieve Website. No Internet Connection?")
else:
self.title.pack_forget()
self.main1.pack_forget()
self.next.pack_forget()
fpl = FrontPageList(self.currMaster, 'Associated Press', currlinks, currtitles, currcategories,
self.currPage)
def ny_listen(self, event):
# Grab the list of links and titles from the front page of nytimes. See grabheadline.py
currlinks, currtitles, currcategories = grabheadline.grabfront('https://nytimes.com')
# If there are no links to be grabbed, it must mean there's no Internet connection
if len(currlinks) == 0:
tk.messagebox.showerror("Error", "Failed to Retrieve Website. No Internet Connection?")
else:
# Replace the GUI of the front grid with the generated headline list of the clicked website (i.e nytimes here)
self.title.pack_forget()
self.main1.pack_forget()
self.next.pack_forget()
fpl = FrontPageList(self.currMaster, 'New York Times', currlinks, currtitles, currcategories, self.currPage)
def graball():
# Takes around 160-180s for 200 articles, way too slow
prev = time.time()
list_news = ['https://nytimes.com', 'https://reuters.com', 'https://bbc.com',
'https://www.theguardian.com/international', 'https://apnews.com',
'https://latimes.com', 'http://huffpost.com', 'https://www.npr.org/']
links = []
titles = []
categories = []
bags_key = [[]]
keywords = dict()
for source in list_news:
prevt = time.time()
templinks, temptitles, tempcategories = grabheadline.grabfront(source)
# print(templinks)
links.extend(templinks)
titles.extend(temptitles)
categories.extend(tempcategories)
print(time.time() - prevt)
for link in links:
print(link)
prevt = time.time()
currkeys = lxrTest.generateKeywords(link)
bags_key.append(currkeys)
# print(type(currkeys))
for key in currkeys:
if key in keywords.keys():
keywords[key] = keywords[key] + 1
else:
keywords[key] = 1
print(time.time() - prevt)
sred = sorted(keywords.items(), key=lambda value: value[1], reverse=True)
bags_key = bags_key[1:]
print(sred)
print(time.time() - prev)
def grabfront_wrapper(self, source, pos):
""" Generates a random string of numbers, lower- and uppercase chars. """
templinks, temptitles, tempcategories = grabheadline.grabfront(source)
print(templinks)
print('[RESULT] FINISHED GRABBING from ' + source)
return pos, templinks, temptitles
def grabfront_wrapper(source, pos):
""" Generates a random string of numbers, lower- and uppercase chars. """
templinks, temptitles, tempcategories = grabheadline.grabfront(source)
print(templinks)
print(pos)
return pos, templinks, temptitles, tempcategories