Extracting Data from XML: The program will prompt for a URL, read the XML data from that URL using urllib and then parse and extract the comment counts from the XML data, compute the sum of the numbers in the file.

py4e_ex_13

from urllib import request
import xml.etree.ElementTree as ET

url = 'http://python-data.dr-chuck.net/comments_24966.xml'
print ("Retrieving", url)
html = request.urlopen(url)
data = html.read()
print("Retrieved",len(data),"characters")

tree = ET.fromstring(data)
results = tree.findall('comments/comment')
icount=len(results)
isum=0

for result in results:
    isum += float(result.find('count').text)
print(icount)
print(isum)

import urllib.request, urllib.parse, urllib.error
from bs4 import BeautifulSoup
import xml.etree.ElementTree as ET
import ssl
import re

Ignore SSL certificate errors

ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

url = input('ENTER URL : ') #http://py4e-data.dr-chuck.net/comments_1692183.xml

socket = urllib.request.urlopen(url,context=ctx)

print(socket)

data = socket.read()
data2 = data.decode() #more organized

#print(len(data))
#print(len(data2))

print(data)
print(data2)

tree = ET.fromstring(data2)
fname = tree.findall('comments/comment') #list of all comment tags
counts = tree.findall('.//count')

print(fname)
print(counts)

print(len(fname))

lst = list()

for item in fname:
name = item.find('name').text
print(name)
kount = item.find('count').text
print(kount)

lst.append(int(kount))

print(lst)

sumation = sum(lst)

print(sumation)

MY ANSWER

import urllib.request, urllib.parse, urllib.error import xml.etree.ElementTree as ET import ssl sum = 0

ctx = ssl.create_default_context() ctx.check_hostname = False ctx.verify_mode = ssl.CERT_NONE

url = "http://py4e-data.dr-chuck.net/comments_1659064.xml"

serviceurl = urllib.request.Request(url) uh = urllib.request.urlopen(url, context=ctx) data = uh.read() #print('Retrieved', len(data), 'characters') #print(data.decode()) tree = ET.fromstring(data) lst = tree.findall('comments/comment') #print('User count:', len(lst)) for item in lst: #print('Numero:', item.find('count').text) sum = sum + int(item.find('count').text) print("Total:",sum)

I had a traceback:
"Traceback (most recent call last):
File "/Users/ibraheemalghamdi/Desktop/py4e/xml/xml.py", line 2, in
import xml.etree.ElementTree as ET
File "/Users/ibraheemalghamdi/Desktop/py4e/xml/xml.py", line 2, in
import xml.etree.ElementTree as ET
ModuleNotFoundError: No module named 'xml.etree'; 'xml' is not a package"

Edit: it was the file name. changed it from xml.py to week5.py and worked out. thanks!

why I keep having this error ?
('NoneType' object has no attribute 'text')
import urllib.request, urllib.parse, urllib.error
import ssl
import xml.etree.ElementTree as ET
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
Value = input('Enter location: ')
print('Retrieving',Value)
uh = urllib.request.urlopen(Value, context=ctx)
data = uh.read()
data = data.decode()
tree = ET.fromstring(data)
counts = tree.findall('.//count')
print('Retrieved',len(data),'characters')
counter = 0
sum = 0
for elements in counts:
counter += 1
sum = (elements.find('count').text) + sum
print(counter)
print(sum)

i am getting error :-

Traceback (most recent call last):
File "/Users/shantanusoni/Documents/ImpDoc/shekhar/studie_related/Coding_Culture/Python/python-coursera/example.py", line 2, in
import xml.etree.ElementTree as ET
File "/Users/shantanusoni/Documents/ImpDoc/shekhar/studie_related/Coding_Culture/Python/python-coursera/xml.py", line 2, in
import xml.etree.ElementTree as ET
ModuleNotFoundError: No module named 'xml.etree'; 'xml' is not a package

Plz help me