Merge pull request #158 from Namyalg/Questions-from-Project-Euler

Questions from project euler

Author: powerexploit

System-Automation-Scripts/Questions_from_Project_Euler/README.md

@@ -0,0 +1,29 @@
+# Project Euler #
+
+![Image](./images/euler_home.PNG)
+
+Project Euler is a series of challenging mathematical/computer programming problems that will require more than just mathematical insights to solve
+
+This script written in Python, gets all the 700+ questions across 15 pages which is written into a CSV file named Project_Euler.csv
+
+Beautiful Soup is used for scraping the URL : https://projecteuler.net/archives
+
+Regular expressions have also been used in order to obtain the description of the questions
+
+## Implementation ##
+
+Using **inspect element**, the contents of the page can be understood
+
+The structure of each page is as shown
+
+![Image](./images/euler_questions.PNG)
+
+The <tr> element consists of the description of the question
+
+Each question has the following components
+
+![Image](./images/question1.PNG)
+
+The contents are parsed and stored using Beautiful Soup, a library built for web scraping
+
+

System-Automation-Scripts/Questions_from_Project_Euler/euler.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+
+#Imports and dependencies
+
+import requests
+from bs4 import BeautifulSoup
+import re
+import csv
+
+def Euler():
+  
+  #The contents are written into a CSV file
+  #Each question has a serial number, name of the problem and description of the problem
+
+  with open('Project_Euler.csv', 'w', newline='') as file:
+    writer = csv.writer(file)
+    writer.writerow(["Problem Number", "Name" , "Description"])
+    
+    #There are 15 pages in all, the page number is appended to the URL
+    start = 1
+    pages = 15
+
+    for page in range(start , pages + start):
+      
+      #Response is got from each page, the questions are then searched for 
+      page_url = "https://projecteuler.net/archives;page="+ str(page)
+      response = requests.get(page_url)
+      soup = BeautifulSoup(response.text,"html.parser")
+      
+      #All the questions are located within the <table> tag
+      #This information can be found out by using inspect element, Ctrl+Shift+I
+
+      for link in soup.find('table' , attrs={"id" : "problems_table"}).find_all('a'):
+        
+        #The link to the question is located in a <a> tag
+        question_url = "https://projecteuler.net/" + link['href']
+
+        #The name and question number are obtained
+        question_number = link['href'].split('=')[-1]
+        question_name = link.string
+
+        ques_response = requests.get(question_url)
+        ques_contents = BeautifulSoup(ques_response.text, "html.parser")
+        description = ''
+        
+        #In each question element, the description is mentioned in the <div> tag
+
+        for content in ques_contents.find("div" , attrs={"class":"problem_content"}).children:  
+
+          #The content between the tags are obtained getting rid of the tag elements
+
+          content = re.sub(r'\<.*?>', r' ', str(content))
+          description += content
+        
+        #Each entry is written into the file
+
+        writer.writerow([question_number, question_name , description])
+
+if __name__ == "__main__":
+    Euler() 

System-Automation-Scripts/Questions_from_Project_Euler/images/euler_home.PNG

@@ -0,0 +1,29 @@
+# Project Euler #
+
+![Image](./images/euler_home.PNG)
+
+Project Euler is a series of challenging mathematical/computer programming problems that will require more than just mathematical insights to solve
+
+This script written in Python, gets all the 700+ questions across 15 pages which is written into a CSV file named Project_Euler.csv
+
+Beautiful Soup is used for scraping the URL : https://projecteuler.net/archives
+
+Regular expressions have also been used in order to obtain the description of the questions
+
+## Implementation ##
+
+Using **inspect element**, the contents of the page can be understood
+
+The structure of each page is as shown
+
+![Image](./images/euler_questions.PNG)
+
+The <tr> element consists of the description of the question
+
+Each question has the following components
+
+![Image](./images/question1.PNG)
+
+The contents are parsed and stored using Beautiful Soup, a library built for web scraping
+
+

System-Automation-Scripts/Questions_from_Project_Euler/images/euler_questions.PNG

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+
+#Imports and dependencies
+
+import requests
+from bs4 import BeautifulSoup
+import re
+import csv
+
+def Euler():
+  
+  #The contents are written into a CSV file
+  #Each question has a serial number, name of the problem and description of the problem
+
+  with open('Project_Euler.csv', 'w', newline='') as file:
+    writer = csv.writer(file)
+    writer.writerow(["Problem Number", "Name" , "Description"])
+    
+    #There are 15 pages in all, the page number is appended to the URL
+    start = 1
+    pages = 15
+
+    for page in range(start , pages + start):
+      
+      #Response is got from each page, the questions are then searched for 
+      page_url = "https://projecteuler.net/archives;page="+ str(page)
+      response = requests.get(page_url)
+      soup = BeautifulSoup(response.text,"html.parser")
+      
+      #All the questions are located within the <table> tag
+      #This information can be found out by using inspect element, Ctrl+Shift+I
+
+      for link in soup.find('table' , attrs={"id" : "problems_table"}).find_all('a'):
+        
+        #The link to the question is located in a <a> tag
+        question_url = "https://projecteuler.net/" + link['href']
+
+        #The name and question number are obtained
+        question_number = link['href'].split('=')[-1]
+        question_name = link.string
+
+        ques_response = requests.get(question_url)
+        ques_contents = BeautifulSoup(ques_response.text, "html.parser")
+        description = ''
+        
+        #In each question element, the description is mentioned in the <div> tag
+
+        for content in ques_contents.find("div" , attrs={"class":"problem_content"}).children:  
+
+          #The content between the tags are obtained getting rid of the tag elements
+
+          content = re.sub(r'\<.*?>', r' ', str(content))
+          description += content
+        
+        #Each entry is written into the file
+
+        writer.writerow([question_number, question_name , description])
+
+if __name__ == "__main__":
+    Euler() 

System-Automation-Scripts/Questions_from_Project_Euler/images/question1.PNG

@@ -1,2 +1,2 @@
 # Web-Scraping
-Web scraping is about downloading structured data from the web, selecting some of that data, and passing along what you selected to another process. This folder contains scripts related to web scraping with the help BeautifulSoup , Scrapy , Requests library.
+Web scraping is about downloading structured data from the web, selecting some of that data, and passing along what you selected to another process. This folder contains scripts related to web scraping with the help BeautifulSoup , Scrapy , Requests library.