Last active
August 8, 2023 23:46
-
-
Save sueszli/cd8196dc03df4b0a6a07898db2c64368 to your computer and use it in GitHub Desktop.
scrape all pdf files containing old exams from the semi-structred-data course at TU Wien
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup | |
import os | |
import PyPDF2 | |
EXAM_DIRECTORY_PATH = "./exams" | |
SOLUTION_DIRECTORY_PATH = "./solutions" | |
# parse page | |
url = "https://dbai.tuwien.ac.at/education/ssd/pruefung/" | |
page = requests.get(url) | |
soup = BeautifulSoup(page.content, "html.parser") | |
checkmark = "\u2713" | |
print(checkmark, "Reached website") | |
# scrape links | |
examLinks = [] | |
solutionLinks = [] | |
for link in soup.find_all("a"): | |
href = link.get("href") | |
if href is not None: | |
if href.endswith("-pruefung.pdf"): | |
examLinks.append(href) | |
if href.endswith("-muster.pdf"): | |
solutionLinks.append(href) | |
print(checkmark, "Found", len(examLinks), "exams") | |
print(checkmark, "Found", len(solutionLinks), "exam solution") | |
def downloadPdf(folderName, list): | |
if not os.path.exists(folderName): | |
os.makedirs(folderName) | |
for elem in list: | |
pdf = requests.get(url + elem) | |
path = folderName + "/" + elem | |
file = open(path, "wb") | |
file.write(pdf.content) | |
file.close() | |
print("Downloading exams...") | |
downloadPdf(EXAM_DIRECTORY_PATH, examLinks) | |
print(checkmark, "Downloaded all exams") | |
print("Downloading solutions...") | |
downloadPdf(SOLUTION_DIRECTORY_PATH, solutionLinks) | |
print(checkmark, "Downloaded all solutions") | |
def extractDateFromText(text, elem): | |
date = "" | |
for line in text.split("\n"): | |
if "184.705" in line: | |
date = line.split("184.705", 1)[1] | |
if "181.135" in line: | |
date = line.split("181.135", 1)[1] | |
if date == "": | |
print("Date couldn't be found in ", elem) | |
date = "unknown" | |
date = date.replace(" ", "") | |
# turn DD.MM.YYYY to YYYY.MM.DD | |
elems = date.split(".") | |
return elems[2] + "." + elems[1] + "." + elems[0] | |
def rename(directoryPath): | |
for elem in os.listdir(directoryPath): | |
path = directoryPath + "/" + elem | |
with open(path, "rb") as file: | |
text = PyPDF2.PdfFileReader(file).pages[0].extract_text() | |
date = extractDateFromText(text, elem) | |
newPath = directoryPath + "/" + date + ".pdf" | |
# rename file (add '[V2]' to the end of the file name if it already exists) | |
if not os.path.exists(newPath): | |
os.rename(path, newPath) | |
else: | |
alternativePath = directoryPath + "/" + date + "[V2]" + ".pdf" | |
os.rename(path, alternativePath) | |
print("Changing names of exams to their dates...") | |
rename(EXAM_DIRECTORY_PATH) | |
print(checkmark, "Renamed all exams") | |
print("Changing names of solutions to their dates...") | |
rename(SOLUTION_DIRECTORY_PATH) | |
print(checkmark, "Renamed all solutions") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment