def get_infected_times(filename, meme):
lines = []
domain_times = {}
entries = []
with open(filename, 'r') as f:
for line in f:
line = line.strip()
if (line):
lines.append(line)
else:
entry = Entry(lines)
lines = []
for quote in entry.quotes:
if meme in quote:
entry_domain = entry.get_base_url()
if entry_domain not in domain_times:
domain_times[entry_domain] = [entry.timestamp, None]
for link in entry.links:
link_domain = base_url(link)
if (link_domain != entry_domain
and link_domain in domain_times):
domain_times[link_domain][1] = entry.timestamp
return domain_times
def count_base_urls(file):
lines = []
base_urls = collections.defaultdict(int)
with open(file, 'r') as f:
for line in f:
line = line.strip()
if (line):
lines.append(line)
else:
entry = Entry(lines)
lines = []
# update map
base_urls[entry.get_base_url()] += 1
return base_urls
