How do Telegraph readers die?

import re
import urllib
from bs4 import BeautifulSoup

def get_links_from_page(n, links):
    """Get all obituary links from the page .../deaths/announcements/n.

    There seem to be a maximum of 10 obituaries per page; each page is
    identified by a counting number, n. The set links is updated with the
    URL of each obituary link encountered on this page.

    """

    request = urllib.request.Request('http://announcements.telegraph.co.uk'
                                     '/deaths/announcements/{:d}'.format(n))
    result = urllib.request.urlopen(request)
    resulttext = result.read()
    soup = BeautifulSoup(resulttext,'html.parser')

    # We seek URLs matching the following regex
    patt = 'http:\/\/announcements.telegraph.co.uk\/deaths\/\d+\/[^#]+$'
    for anchor in soup.find_all('a'):
        link = anchor.get('href', '/')
        if re.match(patt, link):
            links.add(link)

# Get the first 1000 obituary URLs.
links = set()
n = 0
while len(links) < 1000:
    n += 1
    print(n)
    get_links_from_page(n, links)

# Save the URLs to a text file.
with open('ps-links.txt', 'w') as fo:
    for link in links:
        print(link, file=fo)

import urllib
from bs4 import BeautifulSoup

def get_obit_from_link(link):
    """Extract the death announcement text from the URL at link."""

    request = urllib.request.Request(link)
    result = urllib.request.urlopen(request)
    resulttext = result.read()
    soup = BeautifulSoup(resulttext,'html.parser')

    # Get the div with the class "detail-ad-text". Make sure there's only one.
    divs = soup.findAll("div", { "class" : "detail-ad-text" })
    if len(divs) != 1:
        print('Skipping link {}: number of matching divs found is {}'
                    .format(link, len(divs)))
        return ''

    # Extract and return the announcement text from the <p> inside this div.
    text = divs[0].p.string
    return text

# Read in the death announcement URL list.
with open('ps-links.txt') as fi:
    links = fi.readlines()

# For each announcement URL, extract the announcement text and write to a file.
with open('obits.txt', 'a') as fo:
    for i, link in enumerate(links):
        link = link.strip()
        print(i+1, link)
        obit_text = get_obit_from_link(link)
        print(obit_text, file=fo)

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.patches import Circle

# Read in the obituaries (one per line)
with open('obits.txt') as fi:
    obits = fi.readlines()

# Count the number of obituaries containing the word "peacefully", the
# words "suddenly" or "unexpectedly", and those containing both.
total = len(obits)
peacefully_count = 0
suddenly_count = 0
both_count = 0
for obit in obits:
    obit = obit.lower()
    peacefully = 'peacefully' in obit
    suddenly = 'suddenly' in obit or 'unexpectedly' in obit
    peacefully_count += peacefully
    suddenly_count += suddenly
    both_count += peacefully and suddenly

print('Peacefully: {}/{}'.format(peacefully_count, total))
print('Suddenly: {}/{}'.format(suddenly_count, total))
print('Both: {}/{}'.format(both_count, total))

# The area of the circles is proportional to the fraction of obituaries in
# each group; their radii are proportional to the square root of their areas.
Ap = peacefully_count/total
As = suddenly_count/total
Ab = both_count/total
# The radius
rp = np.sqrt(Ap)
rs = np.sqrt(As)
rb = np.sqrt(Ab)

# Plot our circles inside a circle or radius 1, representing all obituaries.
fig, ax = plt.subplots(facecolor='w')
ax.set_aspect('equal')
ax.set_xlim(-1,1)
ax.set_ylim(-1,1)
c_all = Circle((0,0), 1, fc='w')

PURPLE = (0.5,0,1,0.6)
ORANGE = (1,0.5,0,0.6)
# The (x, y) centres of the "peacefully" and "suddenly" circles.
cp = (-(1-rp), 0)
cs = (-(1-rp)+0.82,0) # NB hard-code the overlap because it's hard to calculate
c_peacefully = Circle(cp, rp, fc=PURPLE, ec=PURPLE)
c_suddenly = Circle(cs, rs, fc=ORANGE, ec=ORANGE)
for patch in (c_all, c_peacefully, c_suddenly):
    ax.add_artist(patch)

# Annotate with the percentages for each group
cperc = peacefully_count / total * 100
sperc = suddenly_count / total * 100
ax.annotate(s='{:.1f}%'.format(cperc), xy=cp, ha='center', va='center')
ax.annotate(s='Peacefully', xy=(cp[0], -0.15), color='k', ha='center')
ax.annotate(s='{:.1f}%'.format(sperc), xy=cs, ha='center', va='center')
ax.annotate(s='Suddenly', xy=(cs[0], -0.15), color='k', ha='center')

# Displace the title upwards a bit so it's not too close to the big circle.
ax.set_title('How do readers of The Daily Telegraph die?', y=1.05)

plt.axis('off')
plt.show()

peacefully = 'peacefully' in obit
peacefully_count += peacefully