Following Links in Python: The program will use urllib to read the HTML from the data files below, extract the href= vaues from the anchor tags, scan for a tag that is in a particular position relative to the first name in the list, follow that link and repeat the process a number of times and report the last name you find.

py4e_ex_12_02

from bs4 import BeautifulSoup
import urllib.request, urllib.parse, urllib.error
import ssl
import re

ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
url = "http://py4e-data.dr-chuck.net/known_by_Bryce.html"

#to repeat 7 times#
for i in range(7):
    html = urllib.request.urlopen(url, context=ctx).read()
    soup = BeautifulSoup(html, 'html.parser')
    tags = soup('a')
    count = 0
    for tag in tags:
        count = count +1
   
        #make it stop at position 3#
        if count>18:
            break
        url = tag.get('href', None)

print(url)

i also want to share my code as i was finally able to write correct code. it took me while to understand the question so i felt great after seeing positive result an getting this assignmnt done.

import re
import ssl
import urllib.request

from bs4 import BeautifulSoup

lst1 = list()
name_lst = list()
url_lst = list()
url1 = input('enter first url:')
url_lst.append(url1)
repeat = input('enter no of repeats:')
position = int(input('enter url position:')) - 1
count = 0

while count < int(repeat):
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
html = urllib.request.urlopen(url_lst[int(count)], context=ctx).read()
soup = BeautifulSoup(html, 'html.parser')

tags = soup('a')

for tag in tags:
    x = tag.get('href', None)
    lst1.append(x)

url_lst.append(lst1[int(position)])
lst1.clear()
count += 1

for url in url_lst:
y = re.findall('_([a-zA-Z]+).html', url)
name_lst.append(y[0])
print(name_lst)

import urllib.request, urllib.parse, urllib.error
from bs4 import BeautifulSoup
import ssl
lst=[]

ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
url = input('Enter URL - ')
pos= int(input(' Enter position: '))

for i in range(7):

    html = urllib.request.urlopen(url, context=ctx).read()
    soup = BeautifulSoup(html, 'html.parser')

    tags = soup('a')
    for stuff in tags:
            x=stuff.get('href', None)
            lst.append(x)
    url=lst[pos]       
    print(url)
    lst.clear()

Start at: http://py4e-data.dr-chuck.net/known_by_Kedrick.html
Find the link at position 18 (the first name is 1). Follow that link. Repeat this process 7 times. The answer is the last name that you retrieve.
Hint: The first character of the name of the last page that you will load is: L

please help me, I don't know what the problem is!!!! here is my code:

import urllib.request, urllib.parse, urllib.error
import ssl
from bs4 import BeautifulSoup

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

url = "http://py4e-data.dr-chuck.net/known_by_Kedrick.html"

for i in range(7):
html = urllib.request.urlopen(url, context=ctx).read()
soup = BeautifulSoup(html, 'html.parser')
tags = soup('a')
count = 0
for tag in tags:
count = count +1

    if count > 18:
        break
    url = tag.get('href', None)
    name = tag.contents[0]

print(name)

The instructions for this assignment were poorly written and vague. Thank you for the help in clarifying the assignment a bit.

In case of some people if the above code does not work, try the following

import urllib.request, urllib.parse, urllib.error
from bs4 import BeautifulSoup

url = input('Enter URL - ')
html = urllib.request.urlopen(url).read()
soup = BeautifulSoup(html, 'html.parser')

Find all the tags with class="comments"

span_tags = soup.find_all('span', class_='comments')

count = 0
total_sum = 0

for span in span_tags:
# Extract the text content of the span tag and convert to an integer
count += 1
total_sum += int(span.contents[0])

print("Count", count)
print("Sum", total_sum)

Here's how the code works:

It takes the URL as input from the user.
It retrieves the HTML content from the specified URL using urllib.request.urlopen.
It uses BeautifulSoup to parse the HTML and find all the tags with the class "comments" using soup.find_all.
It initializes two variables count and total_sum to keep track of the number of comments and the sum of the comments, respectively.
It iterates through each tag, converts the text content of the tag to an integer using int(span.contents[0]), and adds it to the total_sum.
Finally, it prints the total count and sum of the comments.
When you run the script, it will prompt you to enter the URL (e.g., http://py4e-data.dr-chuck.net/comments_42.html) and then display the count and sum of the comments in the given URL.