Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 5d7c1ec

Browse files
Merge remote-tracking branch 'upstream/master' into Instagram-Follow--NotFollow
2 parents 9b207ff + 9888be7 commit 5d7c1ec

File tree

5 files changed

+323
-0
lines changed

5 files changed

+323
-0
lines changed
Lines changed: 153 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,153 @@
1+
import os
2+
from selenium import webdriver # Automated webdriver
3+
from PIL import Image
4+
from fpdf import FPDF # For converting images to pdf
5+
6+
7+
def select_difficulty():
8+
"""
9+
This function will let user to choose the difficulty level
10+
:return: difficulty_level[]
11+
"""
12+
difficulty_level = []
13+
print("\nEnter the Range of difficulty between 800 to 3500: ")
14+
difficulty_level.append(int(input("Min: ")))
15+
difficulty_level.append(int(input("Max: ")))
16+
17+
return difficulty_level
18+
19+
20+
def extracting_problem_links(diff_level):
21+
"""
22+
This function saves first saves the link of the pages to scrape from
23+
and then the link of every question, saves it in list
24+
:param diff_level: difficulty_level entered by the user
25+
:return pblms_links: consists of all the available questions to scrape
26+
"""
27+
no_of_questions = int(input("\nHow many Questions you want to scrape: "))
28+
29+
pblms_link_scraped = 0
30+
pblms_links = []
31+
page = 1
32+
options = webdriver.ChromeOptions()
33+
options.headless = True
34+
driver = webdriver.Chrome(DRIVER_PATH, options=options)
35+
print("\nRequesting URL ...")
36+
driver.get(f"https://codeforces.com/problemset/?tags={diff_level[0]}-{diff_level[1]}")
37+
38+
# ===================Getting no. of Pages to Scrape=============================
39+
40+
# It will give the total no. of pages present with that question from
41+
# which we are going to scrape
42+
page_links = []
43+
44+
print("\nFinding available pages to scrape....")
45+
46+
available_pages = driver.find_elements_by_css_selector("div.pagination a")
47+
for page_no in available_pages:
48+
page_links.append(page_no.get_attribute("href"))
49+
50+
print(f"Available Pages to scrape are: {len(page_links[:-1])}")
51+
52+
# ===================================================================================
53+
54+
# ***************************** SCRAPING PAGE 1 *************************************
55+
print(f"\nScraping Page {page}")
56+
57+
elements = driver.find_elements_by_css_selector("td.id.dark.left a" and "td.id.left a")
58+
for element in elements:
59+
# Saving the link in pblms_links
60+
pblms_links.append(element.get_attribute("href"))
61+
pblms_link_scraped += 1
62+
63+
# If we scraped required no. of questions then return
64+
if pblms_link_scraped == no_of_questions:
65+
print(f"URLs of Question Scraped till now: {pblms_link_scraped}")
66+
print(f"\nURLs Scrapped Successfully {pblms_link_scraped} out of {no_of_questions}")
67+
return pblms_links
68+
page += 1
69+
print(f"URLs of Question Scraped till now: {pblms_link_scraped}")
70+
# *************************************************************************************
71+
72+
# ----------------------------- SCRAPING SUBSEQUENT PAGES -----------------------------
73+
for link in page_links[1:-1]:
74+
print(f"\nScraping Page {page}")
75+
76+
# Going to next Page
77+
driver.get(link)
78+
elements = driver.find_elements_by_css_selector("td.id.dark.left a" and "td.id.left a")
79+
for element in elements:
80+
# Saving the link in pblms_links
81+
pblms_links.append(element.get_attribute("href"))
82+
pblms_link_scraped += 1
83+
84+
# If we scraped required no. of questions then return
85+
if pblms_link_scraped == no_of_questions:
86+
print(f"URLs of Question Scraped till now: {pblms_link_scraped}")
87+
print(f"\nURLs Scrapped Successfully {pblms_link_scraped} out of {no_of_questions}")
88+
return pblms_links
89+
90+
print(f"URLs of Question Scraped till now: {pblms_link_scraped}")
91+
page += 1
92+
# ----------------------------------------------------------------------------------------------
93+
94+
# scraped all the available questions but still the count is less
95+
print(f"\n{pblms_link_scraped} out of {no_of_questions} URLs able to scrapped !!!")
96+
return pblms_links
97+
98+
99+
def getproblem(URLs):
100+
"""
101+
getproblem() : It takes input from the user of codeforces problemID and difficulty
102+
level and then by using selenium and chrome webdriver, capturing screenshot of the
103+
Codeforces problem using ttypography tag because all the problems of codeforces are
104+
stored inside this div tag and saving it in a image.png file.
105+
Then saving the image.png as pdf file by using fdf library.
106+
"""
107+
108+
path = 'image.png'
109+
110+
# Creating a Target Output Folder
111+
target_folder = './Coderforces_Problem_Scrapper/problems_pdf'
112+
if not os.path.exists(target_folder):
113+
os.makedirs(target_folder)
114+
115+
options = webdriver.ChromeOptions()
116+
# Headless = True for taking a scrolling snapshot
117+
options.headless = True
118+
driver = webdriver.Chrome(DRIVER_PATH, options=options)
119+
file_counter = 1
120+
121+
for url in URLs:
122+
driver.get(url)
123+
# Deciding height by tag
124+
required_height = driver.execute_script(
125+
'return document.body.parentNode.scrollHeight')
126+
driver.set_window_size(1366, required_height)
127+
128+
title = driver.find_element_by_class_name("title").text
129+
filename = title[3:] + '.pdf'
130+
131+
# Taking SS of everything within the ttypography class
132+
driver.find_element_by_class_name('ttypography').screenshot(path)
133+
134+
# Opening image with pillow so based to capture its height and width
135+
cover = Image.open(path)
136+
WIDTH, HEIGHT = cover.size
137+
MARGIN = 10
138+
# based on image's height and width we are adjusting the pdf margin and borders
139+
pdf = FPDF(unit='pt', format=[WIDTH + 2 * MARGIN, HEIGHT + 2 * MARGIN])
140+
pdf.add_page() # Adding new page to the pdf
141+
pdf.image(path, MARGIN, MARGIN)
142+
143+
pdf.output(os.path.join(target_folder, filename), "F") # saving the pdf with the specified filename
144+
print(f'File saved in your directory ./problems_pdf/{filename} ({file_counter}/{len(URLs)}) !')
145+
file_counter += 1
146+
147+
148+
if __name__ == "__main__":
149+
DRIVER_PATH = input("Enter DRIVER PATH location: ")
150+
diff = select_difficulty() # Accepting difficulty level from user
151+
problems_link = extracting_problem_links(diff) # scraping the required the no. of links
152+
getproblem(problems_link) # saving the Questions in PDF file.
153+
os.remove('image.png')

‎Coderforces_Problem_Scrapper/README.md

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
# Save any number of Problem Statement you like from Codeforces as a PDF.
2+
3+
This python script will let you download any number of Problem Statements from Codeforces and save them as a pdf file. The script uses Selenium Webdriver and fpdf library. Selenium is used with Chrome Webdriver, so having Chrome browser is a requirement.
4+
5+
## Setting up:
6+
7+
- Create a virtual environment and activate it.
8+
9+
- Install the requirements
10+
11+
```sh
12+
$ pip install -r requirements.txt
13+
```
14+
15+
## Running the script:
16+
17+
```sh
18+
$ python Codeforces_Problem_Scrapper.py
19+
```
20+
21+
## Terminal Screenshot:
22+
23+
![Imgur](https://i.imgur.com/gqHMxMz.png)
24+
25+
The program will ask you to enter:
26+
1. DRIVER PATH
27+
2. VALID Difficulty Range of PROBLEMS.
28+
3. Number of Questions to Scrape.
29+
30+
## PDF Output:
31+
![Imgur](https://i.imgur.com/1iMC7PE.png)
32+
![GIF](https://media.giphy.com/media/lQ95K1IzUGB2tiqlmZ/giphy.gif)
33+
34+
## Author
35+
[ Akhil Bhalerao ](https://github.com/iamakkkhil)
Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
pillow
2+
fpdf
3+
selenium

‎Script to check Sentiment/Readme.md

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,40 @@
1+
# <b>Sentiment Detector</b>
2+
3+
[![forthebadge](https://forthebadge.com/images/badges/made-with-python.svg)](https://forthebadge.com)
4+
5+
## Sentiment Detector Functionalities : 🚀
6+
7+
- In the input field write the sentence whose sentiment is to be checked
8+
- On clicking on ```check sentiment``` button it displays the percentage of neutral, positive and negative sentiments
9+
- It also displays the overall sentiment
10+
11+
## Sentiment Detector Instructions: 👨🏻‍💻
12+
13+
### Step 1:
14+
15+
Open Termnial 💻
16+
17+
### Step 2:
18+
19+
Locate to the directory where python file is located 📂
20+
21+
### Step 3:
22+
23+
Run the command: python script.py/python3 script.py 🧐
24+
25+
### Step 4:
26+
27+
Sit back and Relax. Let the Script do the Job. ☕
28+
29+
## Requirements
30+
31+
- vaderSentiment
32+
- tkinter
33+
34+
## DEMO
35+
![Screenshot (211)](https://user-images.githubusercontent.com/60662775/115137592-9ac8c000-a044-11eb-83fe-84eaeb549283.png)
36+
37+
## Author
38+
39+
Amit Kumar Mishra
40+

‎Script to check Sentiment/script.py

Lines changed: 92 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,92 @@
1+
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
2+
from tkinter import *
3+
4+
def detect_sentiment():
5+
6+
sentence = textArea.get("1.0", "end")
7+
sid_obj = SentimentIntensityAnalyzer()
8+
9+
sentiment_dict = sid_obj.polarity_scores(sentence)
10+
11+
string = str(sentiment_dict['neg']*100) + "% Negative"
12+
negativeField.insert(10, string)
13+
14+
string = str(sentiment_dict['neu']*100) + "% Neutral"
15+
neutralField.insert(10, string)
16+
17+
string = str(sentiment_dict['pos']*100) +"% Positive"
18+
positiveField.insert(10, string)
19+
20+
if sentiment_dict['compound'] >= 0.05 :
21+
string = "Positive"
22+
23+
elif sentiment_dict['compound'] <= - 0.05 :
24+
string = "Negative"
25+
else :
26+
string = "Neutral"
27+
28+
overallField.insert(10, string)
29+
30+
def clearAll() :
31+
32+
negativeField.delete(0, END)
33+
neutralField.delete(0, END)
34+
positiveField.delete(0, END)
35+
overallField.delete(0, END)
36+
textArea.delete(1.0, END)
37+
38+
39+
gui = Tk()
40+
gui.config(background = "light blue")
41+
gui.title("Sentiment Detector")
42+
43+
gui.geometry("500x500")
44+
enterText = Label(gui, text = "Enter Your Sentence",bg = "light blue")
45+
46+
textArea = Text(gui, height = 10, width = 53, font = "lucida 13")
47+
48+
check = Button(gui, text = "Check Sentiment", fg = "Black",bg = "light yellow", command = detect_sentiment)
49+
negative = Label(gui, text = "sentence was rated as: ",bg = "light blue")
50+
51+
neutral = Label(gui, text = "sentence was rated as: ",bg = "light blue")
52+
53+
positive = Label(gui, text = "sentence was rated as: ",bg = "light blue")
54+
55+
overall = Label(gui, text = "Sentence Overall Rated As: ",bg = "light blue")
56+
57+
negativeField = Entry(gui)
58+
59+
neutralField = Entry(gui)
60+
positiveField = Entry(gui)
61+
overallField = Entry(gui)
62+
clear = Button(gui, text = "Clear", fg = "Black",bg = "light yellow", command = clearAll)
63+
Exit = Button(gui, text = "Exit", fg = "Black",bg = "light yellow", command = exit)
64+
65+
enterText.grid(row = 0, column = 2)
66+
67+
textArea.grid(row = 1, column = 2, padx = 10, sticky = W)
68+
69+
check.grid(row = 2, column = 2)
70+
71+
neutral.grid(row = 3, column = 2)
72+
73+
neutralField.grid(row = 4, column = 2)
74+
75+
positive.grid(row = 5, column = 2)
76+
77+
positiveField.grid(row = 6, column = 2)
78+
79+
negative.grid(row = 7, column = 2)
80+
81+
negativeField.grid(row = 8, column = 2)
82+
83+
overall.grid(row = 9, column = 2)
84+
85+
overallField.grid(row = 10, column = 2)
86+
87+
clear.grid(row = 11, column = 2)
88+
89+
Exit.grid(row = 12, column = 2)
90+
91+
gui.mainloop()
92+

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /