Spaces:
Sleeping
Sleeping
Create base.py
Browse files
base.py
ADDED
@@ -0,0 +1,1067 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import os
|
3 |
+
import re
|
4 |
+
import sys
|
5 |
+
import threading
|
6 |
+
import time
|
7 |
+
import traceback
|
8 |
+
from datetime import datetime, timezone
|
9 |
+
from decimal import Decimal
|
10 |
+
from urllib.parse import parse_qs, unquote, urlparse, urlsplit, urlunparse
|
11 |
+
|
12 |
+
import cloudscraper
|
13 |
+
import requests
|
14 |
+
import rookiepy
|
15 |
+
from bs4 import BeautifulSoup as bs
|
16 |
+
|
17 |
+
from colors import fb, fc, fg, flb, flg, fm, fr, fy
|
18 |
+
|
19 |
+
VERSION = "v2.3.2"
|
20 |
+
|
21 |
+
scraper_dict: dict = {
|
22 |
+
"Udemy Freebies": "uf",
|
23 |
+
"Tutorial Bar": "tb",
|
24 |
+
"Real Discount": "rd",
|
25 |
+
"Course Vania": "cv",
|
26 |
+
"IDownloadCoupons": "idc",
|
27 |
+
"E-next": "en",
|
28 |
+
"Discudemy": "du",
|
29 |
+
}
|
30 |
+
|
31 |
+
LINKS = {
|
32 |
+
"github": "https://github.com/techtanic/Discounted-Udemy-Course-Enroller",
|
33 |
+
"support": "https://techtanic.github.io/duce/support",
|
34 |
+
"discord": "https://discord.gg/wFsfhJh4Rh",
|
35 |
+
}
|
36 |
+
|
37 |
+
|
38 |
+
class LoginException(Exception):
|
39 |
+
"""Login Error
|
40 |
+
|
41 |
+
Args:
|
42 |
+
Exception (str): Exception Reason
|
43 |
+
"""
|
44 |
+
|
45 |
+
pass
|
46 |
+
|
47 |
+
|
48 |
+
class RaisingThread(threading.Thread):
|
49 |
+
def run(self):
|
50 |
+
self._exc = None
|
51 |
+
try:
|
52 |
+
super().run()
|
53 |
+
except Exception as e:
|
54 |
+
self._exc = e
|
55 |
+
|
56 |
+
def join(self, timeout=None):
|
57 |
+
super().join(timeout=timeout)
|
58 |
+
if self._exc:
|
59 |
+
raise self._exc
|
60 |
+
|
61 |
+
|
62 |
+
def resource_path(relative_path):
|
63 |
+
if hasattr(sys, "_MEIPASS"):
|
64 |
+
return os.path.join(sys._MEIPASS, relative_path)
|
65 |
+
return os.path.join(os.path.abspath("."), relative_path)
|
66 |
+
|
67 |
+
|
68 |
+
class Scraper:
|
69 |
+
"""
|
70 |
+
Scrapers: RD,TB, CV, IDC, EN, DU, UF
|
71 |
+
"""
|
72 |
+
|
73 |
+
def __init__(
|
74 |
+
self,
|
75 |
+
site_to_scrape: list = list(scraper_dict.keys()),
|
76 |
+
debug: bool = False,
|
77 |
+
):
|
78 |
+
self.sites = site_to_scrape
|
79 |
+
self.debug = debug
|
80 |
+
for site in self.sites:
|
81 |
+
code_name = scraper_dict[site]
|
82 |
+
setattr(self, f"{code_name}_length", 0)
|
83 |
+
setattr(self, f"{code_name}_data", [])
|
84 |
+
setattr(self, f"{code_name}_done", False)
|
85 |
+
setattr(self, f"{code_name}_progress", 0)
|
86 |
+
setattr(self, f"{code_name}_error", "")
|
87 |
+
|
88 |
+
def get_scraped_courses(self, target: object) -> list:
|
89 |
+
threads = []
|
90 |
+
scraped_data = {}
|
91 |
+
for site in self.sites:
|
92 |
+
t = threading.Thread(
|
93 |
+
target=target,
|
94 |
+
args=(site,),
|
95 |
+
daemon=True,
|
96 |
+
)
|
97 |
+
t.start()
|
98 |
+
threads.append(t)
|
99 |
+
time.sleep(0.2)
|
100 |
+
for t in threads:
|
101 |
+
t.join()
|
102 |
+
for site in self.sites:
|
103 |
+
scraped_data[site] = getattr(self, f"{scraper_dict[site]}_data")
|
104 |
+
return scraped_data
|
105 |
+
|
106 |
+
def append_to_list(self, target: list, title: str, link: str):
|
107 |
+
target.append((title, link))
|
108 |
+
|
109 |
+
def fetch_page_content(self, url: str, headers: dict = None) -> bytes:
|
110 |
+
return requests.get(url, headers=headers).content
|
111 |
+
|
112 |
+
def parse_html(self, content: str):
|
113 |
+
return bs(content, "html5lib")
|
114 |
+
|
115 |
+
def handle_exception(self, site_code: str):
|
116 |
+
setattr(self, f"{site_code}_error", traceback.format_exc())
|
117 |
+
setattr(self, f"{site_code}_length", -1)
|
118 |
+
setattr(self, f"{site_code}_done", True)
|
119 |
+
if self.debug:
|
120 |
+
print(getattr(self, f"{site_code}_error"))
|
121 |
+
|
122 |
+
def cleanup_link(self, link: str) -> str:
|
123 |
+
parsed_url = urlparse(link)
|
124 |
+
|
125 |
+
if parsed_url.netloc == "www.udemy.com":
|
126 |
+
return link
|
127 |
+
|
128 |
+
if parsed_url.netloc == "click.linksynergy.com":
|
129 |
+
query_params = parse_qs(parsed_url.query)
|
130 |
+
|
131 |
+
if "RD_PARM1" in query_params:
|
132 |
+
return unquote(query_params["RD_PARM1"][0])
|
133 |
+
elif "murl" in query_params:
|
134 |
+
return unquote(query_params["murl"][0])
|
135 |
+
else:
|
136 |
+
return ""
|
137 |
+
raise ValueError(f"Unknown link format: {link}")
|
138 |
+
|
139 |
+
def du(self):
|
140 |
+
try:
|
141 |
+
all_items = []
|
142 |
+
head = {
|
143 |
+
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36 Edg/92.0.902.84",
|
144 |
+
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
|
145 |
+
}
|
146 |
+
|
147 |
+
for page in range(1, 4):
|
148 |
+
content = self.fetch_page_content(
|
149 |
+
f"https://www.discudemy.com/all/{page}", headers=head
|
150 |
+
)
|
151 |
+
soup = self.parse_html(content)
|
152 |
+
page_items = soup.find_all("a", {"class": "card-header"})
|
153 |
+
all_items.extend(page_items)
|
154 |
+
self.du_length = len(all_items)
|
155 |
+
if self.debug:
|
156 |
+
print("Length:", self.du_length)
|
157 |
+
for index, item in enumerate(all_items):
|
158 |
+
self.du_progress = index
|
159 |
+
title = item.string
|
160 |
+
url = item["href"].split("/")[-1]
|
161 |
+
content = self.fetch_page_content(
|
162 |
+
f"https://www.discudemy.com/go/{url}", headers=head
|
163 |
+
)
|
164 |
+
soup = self.parse_html(content)
|
165 |
+
link = soup.find("div", {"class": "ui segment"}).a["href"]
|
166 |
+
if self.debug:
|
167 |
+
print(title, link)
|
168 |
+
self.append_to_list(self.du_data, title, link)
|
169 |
+
|
170 |
+
except:
|
171 |
+
self.handle_exception("du")
|
172 |
+
self.du_done = True
|
173 |
+
if self.debug:
|
174 |
+
print("Return Length:", len(self.du_data))
|
175 |
+
|
176 |
+
def uf(self):
|
177 |
+
try:
|
178 |
+
all_items = []
|
179 |
+
for page in range(1, 4):
|
180 |
+
content = self.fetch_page_content(
|
181 |
+
f"https://www.udemyfreebies.com/free-udemy-courses/{page}"
|
182 |
+
)
|
183 |
+
soup = self.parse_html(content)
|
184 |
+
page_items = soup.find_all("a", {"class": "theme-img"})
|
185 |
+
all_items.extend(page_items)
|
186 |
+
self.uf_length = len(all_items)
|
187 |
+
if self.debug:
|
188 |
+
print("Length:", self.uf_length)
|
189 |
+
for index, item in enumerate(all_items):
|
190 |
+
title = item.img["alt"]
|
191 |
+
link = requests.get(
|
192 |
+
f"https://www.udemyfreebies.com/out/{item['href'].split('/')[4]}"
|
193 |
+
).url
|
194 |
+
self.append_to_list(self.uf_data, title, link)
|
195 |
+
self.uf_progress = index
|
196 |
+
|
197 |
+
except:
|
198 |
+
self.handle_exception("uf")
|
199 |
+
self.uf_done = True
|
200 |
+
if self.debug:
|
201 |
+
print("Return Length:", len(self.uf_data))
|
202 |
+
|
203 |
+
def tb(self):
|
204 |
+
try:
|
205 |
+
all_items = []
|
206 |
+
|
207 |
+
for page in range(1, 5):
|
208 |
+
content = self.fetch_page_content(
|
209 |
+
f"https://www.tutorialbar.com/all-courses/page/{page}"
|
210 |
+
)
|
211 |
+
soup = self.parse_html(content)
|
212 |
+
page_items = soup.find_all(
|
213 |
+
"h2", class_="mb15 mt0 font110 mobfont100 fontnormal lineheight20"
|
214 |
+
)
|
215 |
+
all_items.extend(page_items)
|
216 |
+
self.tb_length = len(all_items)
|
217 |
+
if self.debug:
|
218 |
+
print("Length:", self.tb_length)
|
219 |
+
|
220 |
+
for index, item in enumerate(all_items):
|
221 |
+
self.tb_progress = index
|
222 |
+
title = item.a.string
|
223 |
+
url = item.a["href"]
|
224 |
+
content = self.fetch_page_content(url)
|
225 |
+
soup = self.parse_html(content)
|
226 |
+
link = soup.find("a", class_="btn_offer_block re_track_btn")["href"]
|
227 |
+
if "www.udemy.com" in link:
|
228 |
+
self.append_to_list(self.tb_data, title, link)
|
229 |
+
|
230 |
+
except:
|
231 |
+
self.handle_exception("tb")
|
232 |
+
self.tb_done = True
|
233 |
+
if self.debug:
|
234 |
+
print("Return Length:", len(self.tb_data))
|
235 |
+
|
236 |
+
def rd(self):
|
237 |
+
all_items = []
|
238 |
+
|
239 |
+
try:
|
240 |
+
headers = {
|
241 |
+
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36 Edg/92.0.902.84",
|
242 |
+
"Host": "cdn.real.discount",
|
243 |
+
"Connection": "Keep-Alive",
|
244 |
+
"dnt": "1",
|
245 |
+
"referer": "https://www.real.discount/",
|
246 |
+
}
|
247 |
+
try:
|
248 |
+
r = requests.get(
|
249 |
+
"https://cdn.real.discount/api/courses?page=1&limit=500&sortBy=sale_start&store=Udemy&freeOnly=true",
|
250 |
+
headers=headers,
|
251 |
+
timeout=(10, 30),
|
252 |
+
).json()
|
253 |
+
except requests.exceptions.Timeout:
|
254 |
+
self.rd_error = "Timeout"
|
255 |
+
self.rd_length = -1
|
256 |
+
self.rd_done = True
|
257 |
+
return
|
258 |
+
all_items.extend(r["items"])
|
259 |
+
|
260 |
+
self.rd_length = len(all_items)
|
261 |
+
if self.debug:
|
262 |
+
print("Length:", self.rd_length)
|
263 |
+
for index, item in enumerate(all_items):
|
264 |
+
self.rd_progress = index
|
265 |
+
title: str = item["name"]
|
266 |
+
link: str = item["url"]
|
267 |
+
link = self.cleanup_link(link)
|
268 |
+
if link:
|
269 |
+
self.append_to_list(self.rd_data, title, link)
|
270 |
+
|
271 |
+
except:
|
272 |
+
self.handle_exception("rd")
|
273 |
+
if self.debug:
|
274 |
+
print("Return Length:", len(self.rd_data))
|
275 |
+
self.rd_done = True
|
276 |
+
|
277 |
+
def cv(self):
|
278 |
+
try:
|
279 |
+
content = self.fetch_page_content("https://coursevania.com/courses/")
|
280 |
+
soup = self.parse_html(content)
|
281 |
+
try:
|
282 |
+
nonce = json.loads(
|
283 |
+
re.search(
|
284 |
+
r"var stm_lms_nonces = ({.*?});", soup.text, re.DOTALL
|
285 |
+
).group(1)
|
286 |
+
)["load_content"]
|
287 |
+
if self.debug:
|
288 |
+
print("Nonce:", nonce)
|
289 |
+
except IndexError:
|
290 |
+
self.cv_error = "Nonce not found"
|
291 |
+
self.cv_length = -1
|
292 |
+
self.cv_done = True
|
293 |
+
return
|
294 |
+
r = requests.get(
|
295 |
+
"https://coursevania.com/wp-admin/admin-ajax.php?&template=courses/grid&args={%22posts_per_page%22:%2260%22}&action=stm_lms_load_content&nonce="
|
296 |
+
+ nonce
|
297 |
+
+ "&sort=date_high"
|
298 |
+
).json()
|
299 |
+
|
300 |
+
soup = self.parse_html(r["content"])
|
301 |
+
page_items = soup.find_all(
|
302 |
+
"div", {"class": "stm_lms_courses__single--title"}
|
303 |
+
)
|
304 |
+
self.cv_length = len(page_items)
|
305 |
+
if self.debug:
|
306 |
+
print("Small Length:", self.cv_length)
|
307 |
+
for index, item in enumerate(page_items):
|
308 |
+
self.cv_progress = index
|
309 |
+
title = item.h5.string
|
310 |
+
content = self.fetch_page_content(item.a["href"])
|
311 |
+
soup = self.parse_html(content)
|
312 |
+
link = soup.find(
|
313 |
+
"a",
|
314 |
+
{"class": "masterstudy-button-affiliate__link"},
|
315 |
+
)["href"]
|
316 |
+
self.append_to_list(self.cv_data, title, link)
|
317 |
+
|
318 |
+
except:
|
319 |
+
self.handle_exception("cv")
|
320 |
+
self.cv_done = True
|
321 |
+
if self.debug:
|
322 |
+
print("Return Length:", len(self.cv_data))
|
323 |
+
|
324 |
+
def idc(self):
|
325 |
+
try:
|
326 |
+
all_items = []
|
327 |
+
for page in range(1, 5):
|
328 |
+
content = self.fetch_page_content(
|
329 |
+
f"https://idownloadcoupon.com/product-category/udemy/page/{page}"
|
330 |
+
)
|
331 |
+
soup = self.parse_html(content)
|
332 |
+
page_items = soup.find_all(
|
333 |
+
"a",
|
334 |
+
attrs={
|
335 |
+
"class": "woocommerce-LoopProduct-link woocommerce-loop-product__link"
|
336 |
+
},
|
337 |
+
)
|
338 |
+
all_items.extend(page_items)
|
339 |
+
self.idc_length = len(all_items)
|
340 |
+
if self.debug:
|
341 |
+
print("Length:", self.idc_length)
|
342 |
+
for index, item in enumerate(all_items):
|
343 |
+
self.idc_progress = index
|
344 |
+
title = item.h2.string
|
345 |
+
link_num = item["href"].split("/")[4]
|
346 |
+
if link_num == "85":
|
347 |
+
continue
|
348 |
+
link = f"https://idownloadcoupon.com/udemy/{link_num}/"
|
349 |
+
|
350 |
+
r = requests.get(
|
351 |
+
link,
|
352 |
+
allow_redirects=False,
|
353 |
+
)
|
354 |
+
link = unquote(r.headers["Location"])
|
355 |
+
link = self.cleanup_link(link)
|
356 |
+
self.append_to_list(self.idc_data, title, link)
|
357 |
+
|
358 |
+
except:
|
359 |
+
self.handle_exception("idc")
|
360 |
+
self.idc_done = True
|
361 |
+
if self.debug:
|
362 |
+
print("Return Length:", len(self.idc_data))
|
363 |
+
|
364 |
+
def en(self):
|
365 |
+
try:
|
366 |
+
all_items = []
|
367 |
+
for page in range(1, 6):
|
368 |
+
content = self.fetch_page_content(
|
369 |
+
f"https://jobs.e-next.in/course/udemy/{page}"
|
370 |
+
)
|
371 |
+
soup = self.parse_html(content)
|
372 |
+
page_items = soup.find_all(
|
373 |
+
"a", {"class": "btn btn-secondary btn-sm btn-block"}
|
374 |
+
)
|
375 |
+
all_items.extend(page_items)
|
376 |
+
|
377 |
+
self.en_length = len(all_items)
|
378 |
+
|
379 |
+
if self.debug:
|
380 |
+
print("Length:", self.en_length)
|
381 |
+
for index, item in enumerate(all_items):
|
382 |
+
self.en_progress = index
|
383 |
+
content = self.fetch_page_content(item["href"])
|
384 |
+
soup = self.parse_html(content)
|
385 |
+
title = soup.find("h3").string.strip()
|
386 |
+
link = soup.find("a", {"class": "btn btn-primary"})["href"]
|
387 |
+
self.append_to_list(self.en_data, title, link)
|
388 |
+
|
389 |
+
except:
|
390 |
+
self.handle_exception("en")
|
391 |
+
self.en_done = True
|
392 |
+
if self.debug:
|
393 |
+
print("Return Length:", len(self.en_data))
|
394 |
+
print(self.en_data)
|
395 |
+
|
396 |
+
|
397 |
+
class Udemy:
|
398 |
+
def __init__(self, interface: str, debug: bool = False):
|
399 |
+
self.interface = interface
|
400 |
+
# self.client = cloudscraper.CloudScraper()
|
401 |
+
self.client = requests.session()
|
402 |
+
headers = {
|
403 |
+
"User-Agent": "okhttp/4.9.2 UdemyAndroid 8.9.2(499) (phone)",
|
404 |
+
"Accept": "application/json, text/plain, */*",
|
405 |
+
"Accept-Language": "en-GB,en;q=0.5",
|
406 |
+
"Referer": "https://www.udemy.com/",
|
407 |
+
"X-Requested-With": "XMLHttpRequest",
|
408 |
+
"DNT": "1",
|
409 |
+
"Connection": "keep-alive",
|
410 |
+
"Sec-Fetch-Dest": "empty",
|
411 |
+
"Sec-Fetch-Mode": "cors",
|
412 |
+
"Sec-Fetch-Site": "same-origin",
|
413 |
+
"Pragma": "no-cache",
|
414 |
+
"Cache-Control": "no-cache",
|
415 |
+
}
|
416 |
+
|
417 |
+
self.client.headers.update(headers)
|
418 |
+
self.debug = debug
|
419 |
+
|
420 |
+
def print(self, content: str, color: str = "red", **kargs):
|
421 |
+
content = str(content)
|
422 |
+
colours_dict = {
|
423 |
+
"yellow": fy,
|
424 |
+
"red": fr,
|
425 |
+
"blue": fb,
|
426 |
+
"light blue": flb,
|
427 |
+
"green": fg,
|
428 |
+
"light green": flg,
|
429 |
+
"cyan": fc,
|
430 |
+
"magenta": fm,
|
431 |
+
}
|
432 |
+
if self.interface == "gui":
|
433 |
+
self.window["out"].print(content, text_color=color, **kargs)
|
434 |
+
else:
|
435 |
+
print(colours_dict[color] + content, **kargs)
|
436 |
+
|
437 |
+
def get_date_from_utc(self, d: str):
|
438 |
+
utc_dt = datetime.strptime(d, "%Y-%m-%dT%H:%M:%SZ")
|
439 |
+
dt = utc_dt.replace(tzinfo=timezone.utc).astimezone(tz=None)
|
440 |
+
return dt.strftime("%B %d, %Y")
|
441 |
+
|
442 |
+
def get_now_to_utc(self):
|
443 |
+
return datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
|
444 |
+
|
445 |
+
def load_settings(self):
|
446 |
+
try:
|
447 |
+
with open(f"duce-{self.interface}-settings.json") as f:
|
448 |
+
self.settings = json.load(f)
|
449 |
+
except FileNotFoundError:
|
450 |
+
with open(
|
451 |
+
resource_path(f"default-duce-{self.interface}-settings.json")
|
452 |
+
) as f:
|
453 |
+
self.settings = json.load(f)
|
454 |
+
if (
|
455 |
+
self.interface == "cli" and "use_browser_cookies" not in self.settings
|
456 |
+
): # v2.1
|
457 |
+
self.settings.get("use_browser_cookies", False)
|
458 |
+
# v2.2
|
459 |
+
if "course_update_threshold_months" not in self.settings:
|
460 |
+
self.settings["course_update_threshold_months"] = 24 # 2 years
|
461 |
+
|
462 |
+
self.settings["languages"] = dict(
|
463 |
+
sorted(self.settings["languages"].items(), key=lambda item: item[0])
|
464 |
+
)
|
465 |
+
self.save_settings()
|
466 |
+
self.title_exclude = "\n".join(self.settings["title_exclude"])
|
467 |
+
self.instructor_exclude = "\n".join(self.settings["instructor_exclude"])
|
468 |
+
|
469 |
+
def save_settings(self):
|
470 |
+
with open(f"duce-{self.interface}-settings.json", "w") as f:
|
471 |
+
json.dump(self.settings, f, indent=4)
|
472 |
+
|
473 |
+
def make_cookies(self, client_id: str, access_token: str, csrf_token: str):
|
474 |
+
self.cookie_dict = dict(
|
475 |
+
client_id=client_id,
|
476 |
+
access_token=access_token,
|
477 |
+
csrf_token=csrf_token,
|
478 |
+
)
|
479 |
+
|
480 |
+
def fetch_cookies(self):
|
481 |
+
"""Gets cookies from browser
|
482 |
+
Sets cookies_dict, cookie_jar
|
483 |
+
"""
|
484 |
+
cookies = rookiepy.to_cookiejar(rookiepy.load(["www.udemy.com"]))
|
485 |
+
self.cookie_dict: dict = requests.utils.dict_from_cookiejar(cookies)
|
486 |
+
self.cookie_jar = cookies
|
487 |
+
|
488 |
+
def get_enrolled_courses(self):
|
489 |
+
"""Get enrolled courses
|
490 |
+
Sets enrolled_courses
|
491 |
+
|
492 |
+
{slug:enrollment_time}
|
493 |
+
"""
|
494 |
+
next_page = "https://www.udemy.com/api-2.0/users/me/subscribed-courses/?ordering=-enroll_time&fields[course]=enrollment_time,url&page_size=100"
|
495 |
+
courses = {}
|
496 |
+
while next_page:
|
497 |
+
r = self.client.get(
|
498 |
+
next_page,
|
499 |
+
).json()
|
500 |
+
for course in r["results"]:
|
501 |
+
slug = course["url"].split("/")[2]
|
502 |
+
courses[slug] = course["enrollment_time"]
|
503 |
+
next_page = r["next"]
|
504 |
+
self.enrolled_courses = courses
|
505 |
+
|
506 |
+
def compare_versions(self, version1, version2):
|
507 |
+
v1_parts = list(map(int, version1.split(".")))
|
508 |
+
v2_parts = list(map(int, version2.split(".")))
|
509 |
+
max_length = max(len(v1_parts), len(v2_parts))
|
510 |
+
v1_parts.extend([0] * (max_length - len(v1_parts)))
|
511 |
+
v2_parts.extend([0] * (max_length - len(v2_parts)))
|
512 |
+
|
513 |
+
for v1, v2 in zip(v1_parts, v2_parts):
|
514 |
+
if v1 < v2:
|
515 |
+
return -1
|
516 |
+
elif v1 > v2:
|
517 |
+
return 1
|
518 |
+
return 0
|
519 |
+
|
520 |
+
def check_for_update(self) -> tuple[str, str]:
|
521 |
+
r_version = (
|
522 |
+
requests.get(
|
523 |
+
"https://api.github.com/repos/techtanic/Discounted-Udemy-Course-Enroller/releases/latest"
|
524 |
+
)
|
525 |
+
.json()["tag_name"]
|
526 |
+
.removeprefix("v")
|
527 |
+
)
|
528 |
+
c_version = VERSION.removeprefix("v")
|
529 |
+
|
530 |
+
comparison = self.compare_versions(c_version, r_version)
|
531 |
+
|
532 |
+
if comparison == -1:
|
533 |
+
return (
|
534 |
+
f"Update {r_version} Available",
|
535 |
+
f"Update {r_version} Available",
|
536 |
+
)
|
537 |
+
elif comparison == 0:
|
538 |
+
return (
|
539 |
+
f"Login {c_version}",
|
540 |
+
f"Discounted-Udemy-Course-Enroller {c_version}",
|
541 |
+
)
|
542 |
+
else:
|
543 |
+
return (
|
544 |
+
f"Dev Login {c_version}",
|
545 |
+
f"Dev Discounted-Udemy-Course-Enroller {c_version}",
|
546 |
+
)
|
547 |
+
|
548 |
+
def manual_login(self, email: str, password: str):
|
549 |
+
"""Manual Login to Udemy using email and password and sets cookies
|
550 |
+
Args:
|
551 |
+
email (str): Email
|
552 |
+
password (str): Password
|
553 |
+
Raises:
|
554 |
+
LoginException: Login Error
|
555 |
+
"""
|
556 |
+
# s = cloudscraper.CloudScraper()
|
557 |
+
|
558 |
+
s = requests.session()
|
559 |
+
r = s.get(
|
560 |
+
"https://www.udemy.com/join/signup-popup/?locale=en_US&response_type=html&next=https%3A%2F%2Fwww.udemy.com%2Flogout%2F",
|
561 |
+
headers={"User-Agent": "okhttp/4.9.2 UdemyAndroid 8.9.2(499) (phone)"},
|
562 |
+
# headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/119.0",
|
563 |
+
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
|
564 |
+
# 'Accept-Language': 'en-US,en;q=0.5',
|
565 |
+
# #'Accept-Encoding': 'gzip, deflate, br',
|
566 |
+
# 'DNT': '1',
|
567 |
+
# 'Connection': 'keep-alive',
|
568 |
+
# 'Upgrade-Insecure-Requests': '1',
|
569 |
+
# 'Sec-Fetch-Dest': 'document',
|
570 |
+
# 'Sec-Fetch-Mode': 'navigate',
|
571 |
+
# 'Sec-Fetch-Site': 'none',
|
572 |
+
# 'Sec-Fetch-User': '?1',
|
573 |
+
# 'Pragma': 'no-cache',
|
574 |
+
# 'Cache-Control': 'no-cache'},
|
575 |
+
)
|
576 |
+
try:
|
577 |
+
csrf_token = r.cookies["csrftoken"]
|
578 |
+
except:
|
579 |
+
if self.debug:
|
580 |
+
print(r.text)
|
581 |
+
data = {
|
582 |
+
"csrfmiddlewaretoken": csrf_token,
|
583 |
+
"locale": "en_US",
|
584 |
+
"email": email,
|
585 |
+
"password": password,
|
586 |
+
}
|
587 |
+
|
588 |
+
# ss = requests.session()
|
589 |
+
s.cookies.update(r.cookies)
|
590 |
+
s.headers.update(
|
591 |
+
{
|
592 |
+
"User-Agent": "okhttp/4.9.2 UdemyAndroid 8.9.2(499) (phone)",
|
593 |
+
"Accept": "application/json, text/plain, */*",
|
594 |
+
"Accept-Language": "en-GB,en;q=0.5",
|
595 |
+
"Referer": "https://www.udemy.com/join/login-popup/?passwordredirect=True&response_type=json",
|
596 |
+
"Origin": "https://www.udemy.com",
|
597 |
+
"DNT": "1",
|
598 |
+
"Host": "www.udemy.com",
|
599 |
+
"Connection": "keep-alive",
|
600 |
+
"Sec-Fetch-Dest": "empty",
|
601 |
+
"Sec-Fetch-Mode": "cors",
|
602 |
+
"Sec-Fetch-Site": "same-origin",
|
603 |
+
"Pragma": "no-cache",
|
604 |
+
"Cache-Control": "no-cache",
|
605 |
+
}
|
606 |
+
)
|
607 |
+
s = cloudscraper.create_scraper(sess=s)
|
608 |
+
r = s.post(
|
609 |
+
"https://www.udemy.com/join/login-popup/?passwordredirect=True&response_type=json",
|
610 |
+
data=data,
|
611 |
+
allow_redirects=False,
|
612 |
+
)
|
613 |
+
if r.text.__contains__("returnUrl"):
|
614 |
+
self.make_cookies(
|
615 |
+
r.cookies["client_id"], r.cookies["access_token"], csrf_token
|
616 |
+
)
|
617 |
+
else:
|
618 |
+
login_error = r.json()["error"]["data"]["formErrors"][0]
|
619 |
+
if login_error[0] == "Y":
|
620 |
+
raise LoginException("Too many logins per hour try later")
|
621 |
+
elif login_error[0] == "T":
|
622 |
+
raise LoginException("Email or password incorrect")
|
623 |
+
else:
|
624 |
+
raise LoginException(login_error)
|
625 |
+
|
626 |
+
def get_session_info(self):
|
627 |
+
"""Get Session info
|
628 |
+
Sets Client Session, currency and name
|
629 |
+
"""
|
630 |
+
s = cloudscraper.CloudScraper()
|
631 |
+
# headers = {
|
632 |
+
# "authorization": "Bearer " + self.cookie_dict["access_token"],
|
633 |
+
# "accept": "application/json, text/plain, */*",
|
634 |
+
# "x-requested-with": "XMLHttpRequest",
|
635 |
+
# "x-forwarded-for": str(
|
636 |
+
# ".".join(map(str, (random.randint(0, 255) for _ in range(4))))
|
637 |
+
# ),
|
638 |
+
# "x-udemy-authorization": "Bearer " + self.cookie_dict["access_token"],
|
639 |
+
# "content-type": "application/json;charset=UTF-8",
|
640 |
+
# "origin": "https://www.udemy.com",
|
641 |
+
# "referer": "https://www.udemy.com/",
|
642 |
+
# "dnt": "1",
|
643 |
+
# "User-Agent": "okhttp/4.9.2 UdemyAndroid 8.9.2(499) (phone)",
|
644 |
+
# }
|
645 |
+
|
646 |
+
headers = {
|
647 |
+
"User-Agent": "okhttp/4.9.2 UdemyAndroid 8.9.2(499) (phone)",
|
648 |
+
"Accept": "application/json, text/plain, */*",
|
649 |
+
"Accept-Language": "en-GB,en;q=0.5",
|
650 |
+
"Referer": "https://www.udemy.com/",
|
651 |
+
"X-Requested-With": "XMLHttpRequest",
|
652 |
+
"DNT": "1",
|
653 |
+
"Connection": "keep-alive",
|
654 |
+
"Sec-Fetch-Dest": "empty",
|
655 |
+
"Sec-Fetch-Mode": "cors",
|
656 |
+
"Sec-Fetch-Site": "same-origin",
|
657 |
+
"Pragma": "no-cache",
|
658 |
+
"Cache-Control": "no-cache",
|
659 |
+
}
|
660 |
+
r = s.get(
|
661 |
+
"https://www.udemy.com/api-2.0/contexts/me/?header=True",
|
662 |
+
cookies=self.cookie_dict,
|
663 |
+
headers=headers,
|
664 |
+
)
|
665 |
+
r = r.json()
|
666 |
+
if self.debug:
|
667 |
+
print(r)
|
668 |
+
if not r["header"]["isLoggedIn"]:
|
669 |
+
raise LoginException("Login Failed")
|
670 |
+
|
671 |
+
self.display_name: str = r["header"]["user"]["display_name"]
|
672 |
+
r = s.get(
|
673 |
+
"https://www.udemy.com/api-2.0/shopping-carts/me/",
|
674 |
+
headers=headers,
|
675 |
+
cookies=self.cookie_dict,
|
676 |
+
)
|
677 |
+
r = r.json()
|
678 |
+
self.currency: str = r["user"]["credit"]["currency_code"]
|
679 |
+
|
680 |
+
s = cloudscraper.CloudScraper()
|
681 |
+
s.cookies.update(self.cookie_dict)
|
682 |
+
s.headers.update(headers)
|
683 |
+
s.keep_alive = False
|
684 |
+
self.client = s
|
685 |
+
self.get_enrolled_courses()
|
686 |
+
|
687 |
+
def is_keyword_excluded(self, title: str) -> bool:
|
688 |
+
title_words = title.casefold().split()
|
689 |
+
for word in title_words:
|
690 |
+
word = word.casefold()
|
691 |
+
if word in self.title_exclude:
|
692 |
+
return True
|
693 |
+
return False
|
694 |
+
|
695 |
+
def is_instructor_excluded(self, instructors: list) -> bool:
|
696 |
+
for instructor in instructors:
|
697 |
+
if instructor in self.settings["instructor_exclude"]:
|
698 |
+
return True
|
699 |
+
return False
|
700 |
+
|
701 |
+
def is_course_updated(self, last_update: str | None) -> bool:
|
702 |
+
if not last_update:
|
703 |
+
return True
|
704 |
+
current_date = datetime.now()
|
705 |
+
last_update_date = datetime.strptime(last_update, "%Y-%m-%d")
|
706 |
+
# Calculate the difference in years and months
|
707 |
+
years = current_date.year - last_update_date.year
|
708 |
+
months = current_date.month - last_update_date.month
|
709 |
+
days = current_date.day - last_update_date.day
|
710 |
+
|
711 |
+
# Adjust the months and years if necessary
|
712 |
+
if days < 0:
|
713 |
+
months -= 1
|
714 |
+
|
715 |
+
if months < 0:
|
716 |
+
years -= 1
|
717 |
+
months += 12
|
718 |
+
|
719 |
+
# Calculate the total month difference
|
720 |
+
month_diff = years * 12 + months
|
721 |
+
return month_diff < self.settings["course_update_threshold_months"]
|
722 |
+
|
723 |
+
def is_user_dumb(self) -> bool:
|
724 |
+
self.sites = [key for key, value in self.settings["sites"].items() if value]
|
725 |
+
self.categories = [
|
726 |
+
key for key, value in self.settings["categories"].items() if value
|
727 |
+
]
|
728 |
+
self.languages = [
|
729 |
+
key for key, value in self.settings["languages"].items() if value
|
730 |
+
]
|
731 |
+
self.instructor_exclude = self.settings["instructor_exclude"]
|
732 |
+
self.title_exclude = self.settings["title_exclude"]
|
733 |
+
self.min_rating = self.settings["min_rating"]
|
734 |
+
return not all([bool(self.sites), bool(self.categories), bool(self.languages)])
|
735 |
+
|
736 |
+
def save_course(self):
|
737 |
+
if self.settings["save_txt"]:
|
738 |
+
self.txt_file.write(f"{self.title} - {self.link}\n")
|
739 |
+
self.txt_file.flush()
|
740 |
+
os.fsync(self.txt_file.fileno())
|
741 |
+
|
742 |
+
def remove_duplicate_courses(self):
|
743 |
+
existing_links = set()
|
744 |
+
new_data = {}
|
745 |
+
for key, courses in self.scraped_data.items():
|
746 |
+
new_data[key] = []
|
747 |
+
for title, link in courses:
|
748 |
+
link = self.normalize_link(link)
|
749 |
+
if link not in existing_links:
|
750 |
+
new_data[key].append((title, link))
|
751 |
+
existing_links.add(link)
|
752 |
+
self.scraped_data = {k: v for k, v in new_data.items() if v}
|
753 |
+
|
754 |
+
def normalize_link(self, link):
|
755 |
+
parsed_url = urlparse(link)
|
756 |
+
path = (
|
757 |
+
parsed_url.path if parsed_url.path.endswith("/") else parsed_url.path + "/"
|
758 |
+
)
|
759 |
+
return urlunparse(
|
760 |
+
(
|
761 |
+
parsed_url.scheme,
|
762 |
+
parsed_url.netloc,
|
763 |
+
path,
|
764 |
+
parsed_url.params,
|
765 |
+
parsed_url.query,
|
766 |
+
parsed_url.fragment,
|
767 |
+
)
|
768 |
+
)
|
769 |
+
|
770 |
+
def get_course_id(self, url):
|
771 |
+
course = {
|
772 |
+
"course_id": None,
|
773 |
+
"url": url,
|
774 |
+
"is_invalid": False,
|
775 |
+
"is_free": None,
|
776 |
+
"is_excluded": None,
|
777 |
+
"retry": None,
|
778 |
+
"msg": "Report to developer",
|
779 |
+
}
|
780 |
+
url = re.sub(r"\W+$", "", unquote(url))
|
781 |
+
try:
|
782 |
+
r = self.client.get(url)
|
783 |
+
except requests.exceptions.ConnectionError:
|
784 |
+
if self.debug:
|
785 |
+
print(r.text)
|
786 |
+
course["retry"] = True
|
787 |
+
return course
|
788 |
+
course["url"] = r.url
|
789 |
+
soup = bs(r.content, "html5lib")
|
790 |
+
|
791 |
+
course_id = soup.find("body").get("data-clp-course-id", "invalid")
|
792 |
+
|
793 |
+
if course_id == "invalid":
|
794 |
+
course["is_invalid"] = True
|
795 |
+
course["msg"] = "Course ID not found: Report to developer"
|
796 |
+
return course
|
797 |
+
course["course_id"] = course_id
|
798 |
+
dma = json.loads(soup.find("body")["data-module-args"])
|
799 |
+
if self.debug:
|
800 |
+
with open("debug/dma.json", "w") as f:
|
801 |
+
json.dump(dma, f, indent=4)
|
802 |
+
|
803 |
+
if dma.get("view_restriction"):
|
804 |
+
course["is_invalid"] = True
|
805 |
+
course["msg"] = dma["serverSideProps"]["limitedAccess"]["errorMessage"][
|
806 |
+
"title"
|
807 |
+
]
|
808 |
+
return course
|
809 |
+
|
810 |
+
course["is_free"] = not dma["serverSideProps"]["course"].get("isPaid", True)
|
811 |
+
if not self.debug and self.is_course_excluded(dma):
|
812 |
+
course["is_excluded"] = True
|
813 |
+
return course
|
814 |
+
|
815 |
+
return course
|
816 |
+
|
817 |
+
def is_course_excluded(self, dma):
|
818 |
+
instructors = [
|
819 |
+
i["absolute_url"].split("/")[-2]
|
820 |
+
for i in dma["serverSideProps"]["course"]["instructors"]["instructors_info"]
|
821 |
+
if i["absolute_url"]
|
822 |
+
]
|
823 |
+
lang = dma["serverSideProps"]["course"]["localeSimpleEnglishTitle"]
|
824 |
+
cat = dma["serverSideProps"]["topicMenu"]["breadcrumbs"][0]["title"]
|
825 |
+
rating = dma["serverSideProps"]["course"]["rating"]
|
826 |
+
last_update = dma["serverSideProps"]["course"]["lastUpdateDate"]
|
827 |
+
|
828 |
+
if not self.is_course_updated(last_update):
|
829 |
+
self.print(
|
830 |
+
f"Course excluded: Last updated {last_update}", color="light blue"
|
831 |
+
)
|
832 |
+
elif self.is_instructor_excluded(instructors):
|
833 |
+
self.print(f"Instructor excluded: {instructors[0]}", color="light blue")
|
834 |
+
elif self.is_keyword_excluded(self.title):
|
835 |
+
self.print("Keyword Excluded", color="light blue")
|
836 |
+
elif cat not in self.categories:
|
837 |
+
self.print(f"Category excluded: {cat}", color="light blue")
|
838 |
+
elif lang not in self.languages:
|
839 |
+
self.print(f"Language excluded: {lang}", color="light blue")
|
840 |
+
elif rating < self.min_rating:
|
841 |
+
self.print(f"Low rating: {rating}", color="light blue")
|
842 |
+
else:
|
843 |
+
return False
|
844 |
+
return True
|
845 |
+
|
846 |
+
def extract_course_coupon(self, url):
|
847 |
+
params = parse_qs(urlsplit(url).query)
|
848 |
+
return params.get("couponCode", [False])[0]
|
849 |
+
|
850 |
+
def check_course(self, course_id, coupon_code=None):
|
851 |
+
url = f"https://www.udemy.com/api-2.0/course-landing-components/{course_id}/me/?components=purchase"
|
852 |
+
if coupon_code:
|
853 |
+
url += f",redeem_coupon&couponCode={coupon_code}"
|
854 |
+
|
855 |
+
r = self.client.get(url).json()
|
856 |
+
if self.debug:
|
857 |
+
with open("test/check_course.json", "w") as f:
|
858 |
+
json.dump(r, f, indent=4)
|
859 |
+
amount = (
|
860 |
+
r.get("purchase", {})
|
861 |
+
.get("data", {})
|
862 |
+
.get("list_price", {})
|
863 |
+
.get("amount", "retry")
|
864 |
+
)
|
865 |
+
coupon_valid = False
|
866 |
+
|
867 |
+
if coupon_code and "redeem_coupon" in r:
|
868 |
+
discount = r["purchase"]["data"]["pricing_result"]["discount_percent"]
|
869 |
+
status = r["redeem_coupon"]["discount_attempts"][0]["status"]
|
870 |
+
coupon_valid = discount == 100 and status == "applied"
|
871 |
+
|
872 |
+
return Decimal(amount), coupon_valid
|
873 |
+
|
874 |
+
def start_enrolling(self):
|
875 |
+
self.remove_duplicate_courses()
|
876 |
+
self.initialize_counters()
|
877 |
+
self.setup_txt_file()
|
878 |
+
|
879 |
+
total_courses = sum(len(courses) for courses in self.scraped_data.values())
|
880 |
+
previous_courses_count = 0
|
881 |
+
for site_index, (site, courses) in enumerate(self.scraped_data.items()):
|
882 |
+
self.print(f"\nSite: {site} [{len(courses)}]", color="cyan")
|
883 |
+
|
884 |
+
for index, (title, link) in enumerate(courses):
|
885 |
+
self.title = title
|
886 |
+
self.link = link
|
887 |
+
self.print_course_info(previous_courses_count + index, total_courses)
|
888 |
+
self.handle_course_enrollment()
|
889 |
+
previous_courses_count += len(courses)
|
890 |
+
|
891 |
+
def initialize_counters(self):
|
892 |
+
self.successfully_enrolled_c = 0
|
893 |
+
self.already_enrolled_c = 0
|
894 |
+
self.expired_c = 0
|
895 |
+
self.excluded_c = 0
|
896 |
+
self.amount_saved_c = 0
|
897 |
+
|
898 |
+
def setup_txt_file(self):
|
899 |
+
if self.settings["save_txt"]:
|
900 |
+
os.makedirs("Courses/", exist_ok=True)
|
901 |
+
self.txt_file = open(
|
902 |
+
f"Courses/{time.strftime('%Y-%m-%d--%H-%M')}.txt", "w", encoding="utf-8"
|
903 |
+
)
|
904 |
+
|
905 |
+
def print_course_info(self, index, total_courses):
|
906 |
+
self.print(f"[{index + 1} / {total_courses}] ", color="magenta", end=" ")
|
907 |
+
self.print(self.title, color="yellow", end=" ")
|
908 |
+
self.print(self.link, color="blue")
|
909 |
+
|
910 |
+
def handle_course_enrollment(self):
|
911 |
+
slug = self.link.split("/")[4]
|
912 |
+
|
913 |
+
if slug in self.enrolled_courses:
|
914 |
+
self.print(
|
915 |
+
f"You purchased this course on {self.get_date_from_utc(self.enrolled_courses[slug])}",
|
916 |
+
color="light blue",
|
917 |
+
)
|
918 |
+
self.already_enrolled_c += 1
|
919 |
+
return
|
920 |
+
|
921 |
+
course = self.get_course_id(self.link)
|
922 |
+
if course["is_invalid"]:
|
923 |
+
self.print(course["msg"], color="red")
|
924 |
+
self.excluded_c += 1
|
925 |
+
elif course["retry"]:
|
926 |
+
self.print("Retrying...", color="red")
|
927 |
+
time.sleep(1)
|
928 |
+
self.handle_course_enrollment()
|
929 |
+
elif course["is_excluded"]:
|
930 |
+
self.excluded_c += 1
|
931 |
+
elif course["is_free"]:
|
932 |
+
self.handle_free_course(course["course_id"])
|
933 |
+
elif not course["is_free"]:
|
934 |
+
self.handle_discounted_course(course["course_id"])
|
935 |
+
else:
|
936 |
+
self.print("Unknown Error: Report this link to the developer", color="red")
|
937 |
+
self.excluded_c += 1
|
938 |
+
|
939 |
+
def handle_free_course(self, course_id):
|
940 |
+
if self.settings["discounted_only"]:
|
941 |
+
self.print("Free course excluded", color="light blue")
|
942 |
+
self.excluded_c += 1
|
943 |
+
else:
|
944 |
+
success = self.free_checkout(course_id)
|
945 |
+
if success:
|
946 |
+
self.print("Successfully Subscribed", color="green")
|
947 |
+
self.successfully_enrolled_c += 1
|
948 |
+
self.save_course()
|
949 |
+
else:
|
950 |
+
self.print(
|
951 |
+
"Unknown Error: Report this link to the developer", color="red"
|
952 |
+
)
|
953 |
+
self.expired_c += 1
|
954 |
+
|
955 |
+
def discounted_checkout(self, coupon, course_id) -> dict:
|
956 |
+
payload = {
|
957 |
+
"checkout_environment": "Marketplace",
|
958 |
+
"checkout_event": "Submit",
|
959 |
+
"payment_info": {
|
960 |
+
"method_id": "0",
|
961 |
+
"payment_method": "free-method",
|
962 |
+
"payment_vendor": "Free",
|
963 |
+
},
|
964 |
+
"shopping_info": {
|
965 |
+
"items": [
|
966 |
+
{
|
967 |
+
"buyable": {"id": course_id, "type": "course"},
|
968 |
+
"discountInfo": {"code": coupon},
|
969 |
+
"price": {"amount": 0, "currency": self.currency.upper()},
|
970 |
+
}
|
971 |
+
],
|
972 |
+
"is_cart": False,
|
973 |
+
},
|
974 |
+
}
|
975 |
+
headers = {
|
976 |
+
"User-Agent": "okhttp/4.9.2 UdemyAndroid 8.9.2(499) (phone)",
|
977 |
+
"Accept": "application/json, text/plain, */*",
|
978 |
+
"Accept-Language": "en-US",
|
979 |
+
"Referer": f"https://www.udemy.com/payment/checkout/express/course/{course_id}/?discountCode={coupon}",
|
980 |
+
"Content-Type": "application/json",
|
981 |
+
"X-Requested-With": "XMLHttpRequest",
|
982 |
+
"x-checkout-is-mobile-app": "false",
|
983 |
+
"Origin": "https://www.udemy.com",
|
984 |
+
"DNT": "1",
|
985 |
+
"Sec-GPC": "1",
|
986 |
+
"Connection": "keep-alive",
|
987 |
+
"Sec-Fetch-Dest": "empty",
|
988 |
+
"Sec-Fetch-Mode": "cors",
|
989 |
+
"Sec-Fetch-Site": "same-origin",
|
990 |
+
"Priority": "u=0",
|
991 |
+
}
|
992 |
+
# csrftoken = None
|
993 |
+
# for cookie in self.client.cookies:
|
994 |
+
# if cookie.name == "csrftoken":
|
995 |
+
# csrftoken = cookie.value
|
996 |
+
# break
|
997 |
+
|
998 |
+
# if csrftoken:
|
999 |
+
# headers["X-CSRFToken"] = csrftoken
|
1000 |
+
# else:
|
1001 |
+
# raise ValueError("CSRF token not found")
|
1002 |
+
|
1003 |
+
r = self.client.post(
|
1004 |
+
"https://www.udemy.com/payment/checkout-submit/",
|
1005 |
+
json=payload,
|
1006 |
+
headers=headers,
|
1007 |
+
)
|
1008 |
+
try:
|
1009 |
+
r = r.json()
|
1010 |
+
except:
|
1011 |
+
self.print(r.text, color="red")
|
1012 |
+
self.print("Unknown Error: Report this to the developer", color="red")
|
1013 |
+
return {"status": "failed", "message": "Unknown Error"}
|
1014 |
+
return r
|
1015 |
+
|
1016 |
+
def free_checkout(self, course_id):
|
1017 |
+
self.client.get(f"https://www.udemy.com/course/subscribe/?courseId={course_id}")
|
1018 |
+
r = self.client.get(
|
1019 |
+
f"https://www.udemy.com/api-2.0/users/me/subscribed-courses/{course_id}/?fields%5Bcourse%5D=%40default%2Cbuyable_object_type%2Cprimary_subcategory%2Cis_private"
|
1020 |
+
).json()
|
1021 |
+
return r.get("_class") == "course"
|
1022 |
+
|
1023 |
+
def handle_discounted_course(self, course_id):
|
1024 |
+
coupon_code = self.extract_course_coupon(self.link)
|
1025 |
+
amount, coupon_valid = self.check_course(course_id, coupon_code)
|
1026 |
+
if amount == "retry":
|
1027 |
+
self.print("Retrying...", color="red")
|
1028 |
+
time.sleep(1)
|
1029 |
+
self.handle_discounted_course(course_id)
|
1030 |
+
elif coupon_valid: # elif coupon_code and coupon_valid:
|
1031 |
+
self.process_coupon(course_id, coupon_code, amount)
|
1032 |
+
else:
|
1033 |
+
self.print("Coupon Expired", color="red")
|
1034 |
+
self.expired_c += 1
|
1035 |
+
|
1036 |
+
def process_coupon(self, course_id, coupon_code, amount):
|
1037 |
+
checkout_response = self.discounted_checkout(coupon_code, course_id)
|
1038 |
+
if msg := checkout_response.get("detail"):
|
1039 |
+
self.print(msg, color="red")
|
1040 |
+
try:
|
1041 |
+
wait_time = int(re.search(r"\d+", checkout_response["detail"]).group(0))
|
1042 |
+
except:
|
1043 |
+
self.print(
|
1044 |
+
"Unknown Error: Report this link to the developer", color="red"
|
1045 |
+
)
|
1046 |
+
self.print(checkout_response, color="red")
|
1047 |
+
wait_time = 60
|
1048 |
+
time.sleep(wait_time + 1.5)
|
1049 |
+
self.process_coupon(course_id, coupon_code, amount)
|
1050 |
+
elif checkout_response["status"] == "succeeded":
|
1051 |
+
self.print("Successfully Enrolled To Course :)", color="green")
|
1052 |
+
self.successfully_enrolled_c += 1
|
1053 |
+
self.enrolled_courses[course_id] = self.get_now_to_utc()
|
1054 |
+
self.amount_saved_c += amount
|
1055 |
+
self.save_course()
|
1056 |
+
time.sleep(3.8)
|
1057 |
+
elif checkout_response["status"] == "failed":
|
1058 |
+
message = checkout_response["message"]
|
1059 |
+
if "item_already_subscribed" in message:
|
1060 |
+
self.print("Already Enrolled", color="light blue")
|
1061 |
+
self.already_enrolled_c += 1
|
1062 |
+
else:
|
1063 |
+
self.print("Unknown Error: Report this to the developer", color="red")
|
1064 |
+
self.print(checkout_response, color="red")
|
1065 |
+
else:
|
1066 |
+
self.print("Unknown Error: Report this to the developer", color="red")
|
1067 |
+
self.print(checkout_response, color="red")
|