Instantly share code, notes, and snippets.
Created
September 26, 2022 18:08
-
Star
0
(0)
You must be signed in to star a gist -
Fork
0
(0)
You must be signed in to fork a gist
-
Save rodjul/206028918f3e94166c7bb58fb6c9a38a to your computer and use it in GitHub Desktop.
Slide Share download templates
This file contains hidden or 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 | |
| from getpass import getpass | |
| import os | |
| import threading | |
| headers = { | |
| "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36", | |
| "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", | |
| "Accept-Language": "pt-BR,pt;q=0.8,en-US;q=0.5,en;q=0.3", | |
| "Accept-Encoding": "gzip, deflate", | |
| "Connection": "close", | |
| "Referer": "https://slidemodel.com/", | |
| "Upgrade-Insecure-Requests": "1" | |
| } | |
| # proxy = {"http":"http://127.0.0.1:8080", "https":"http://127.0.0.1:8080"} | |
| proxy = {} | |
| session = requests.Session() | |
| folder = "templates" | |
| if not os.path.exists(folder): | |
| os.mkdir(folder) | |
| def get_length_pages(anchors) -> int: | |
| ''' | |
| Parse nav page in https://slidemodel.com/templates/ | |
| Returns: | |
| total pages | |
| ''' | |
| nav_pages = [b for b in anchors if b.attrs.get('class') and b.attrs['class'][0] == "page-numbers"] | |
| return int( nav_pages[len(nav_pages)-1].text ) | |
| def get_template_items(anchors) -> list: | |
| ''' | |
| Obtain all template items (12 in total per page) | |
| ''' | |
| return [b for b in anchors if b.attrs.get('class') and b.attrs['class'][0] == "item-thumbnail"] | |
| def download_template(page, total_pages, item): | |
| url = item.attrs['href'] | |
| template_page = session.get(url, headers=headers) | |
| template_soup = BeautifulSoup(template_page.content, 'html.parser') | |
| inputs = template_soup.find_all("input") | |
| magn_ddaid = 0 | |
| magn_ddid = 0 | |
| for input in inputs: | |
| if input.attrs.get("name") and input.attrs['name'] == "magn-ddaid": | |
| magn_ddaid = input.attrs['value'] | |
| if input.attrs.get("name") and input.attrs['name'] == "magn-ddid": | |
| magn_ddid = input.attrs['value'] | |
| # labels = template_soup.find_all("label") | |
| # filename = [label for label in labels if label.attrs.get("for") and label.attrs["for"][0] == magn_ddaid][0] | |
| label = template_soup.find("label") | |
| filename = label.attrs['title'] | |
| filename = filename.replace("'", "").replace("`","") | |
| category = template_soup.find_all("dd")[0].text | |
| category = category.rstrip() | |
| try: | |
| if not os.path.exists(folder + "/" + category): | |
| os.mkdir(folder + "/" + category) | |
| except Exception as e: | |
| print(e) | |
| try: | |
| print(f"Downloading item from page {page} of {total_pages} - {category}/{filename}") | |
| download_file = session.post("https://slidemodel.com/download/", headers=headers, data={"magn-ddid":magn_ddid, "magn-ddaid":magn_ddaid }, proxies=proxy) | |
| with open(folder + "/" + category + "/" + filename, "wb") as f: | |
| f.write(download_file.content) | |
| except Exception as e: | |
| print(f"ERROR: failed to download {filename} - {url}") | |
| def main(): | |
| # https://slidemodel.com/templates/ | |
| # pegar as paginas 1 ... 258 | |
| # -> a cada <div class="item">, acessar ele e obter os valores: magn-ddaid, magn-ddid e <span class="title" para salvar | |
| url_login = "https://slidemodel.com/account/login/" | |
| username = input("Username: ") | |
| password = getpass() | |
| print("Getting cookies...") | |
| response = session.get(url_login, headers=headers, proxies=proxy) | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| rcp_login_nonce = soup.find_all("input")[7].attrs['value'] | |
| print("Authenticating...") | |
| response = session.post(url_login, data={ | |
| "rcp_user_login":username, | |
| "rcp_user_pass":password, | |
| "rcp_action":"login", | |
| "rcp_redirect":"https://slidemodel.com/account/login/", | |
| "rcp_login_nonce": rcp_login_nonce | |
| }, headers=headers, proxies=proxy) | |
| print("Checking if logged with success") | |
| found = False | |
| for cookie in session.cookies.get_dict().keys(): | |
| if cookie.startswith("wordpress_logged_in"): | |
| found = True | |
| break | |
| if not found: | |
| raise Exception("Invalid credentials") | |
| print("Logged with success") | |
| print("Starting downloading all files") | |
| #first page | |
| page = 1 | |
| response = session.get("https://slidemodel.com/templates/", headers=headers, proxies=proxy) | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| anchors = soup.find_all('a') | |
| total_pages = get_length_pages(anchors) | |
| items = get_template_items(anchors) | |
| threads = [] | |
| for item in items: | |
| # download_template(page, total_pages, item) | |
| t = threading.Thread(target=download_template , args=(page, total_pages, item,)) | |
| threads.append(t) | |
| t.start() | |
| for t in threads: | |
| t.join() | |
| page += 1 | |
| while page <= total_pages: | |
| response = session.get(f"https://slidemodel.com/templates/page/{page}/", headers=headers, proxies=proxy) | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| anchors = soup.find_all('a') | |
| items = get_template_items(anchors) | |
| threads = [] | |
| for item in items: | |
| # download_template(page, total_pages, item) | |
| t = threading.Thread(target=download_template , args=(page, total_pages, item,)) | |
| threads.append(t) | |
| t.start() | |
| for t in threads: | |
| t.join() | |
| page += 1 | |
| if __name__ == "__main__": | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment