-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathCloner.py
198 lines (161 loc) · 5.63 KB
/
Cloner.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
# Web Site Cloning App Mini Project
import os
import requests
import shutil
from bs4 import BeautifulSoup
#import sys
from PyQt5.QtWidgets import QMainWindow, QApplication
from PyQt5 import uic
Ui_MainWindow, QtBaseClass = uic.loadUiType(
"C:/Users/MicroMediA o5/Desktop/clone/clone/GUI.ui")
def save(bs, element, check):
global site_name
global project_path
global project_name
global folder_name
global visited_links
global error_links
links = bs.find_all(element)
for l in links:
href = l.get("href")
if href is not None and href not in visited_links:
if check in href:
href = l.get("href")
print("Working with : {}".format(href))
if "//" in href:
path_s = href.split("/")
file_name = ""
for i in range(3, len(path_s)):
file_name = file_name + "/" + path_s[i]
else:
file_name = href
l = site_name + file_name
try:
r = requests.get(l)
except requests.exceptions.ConnectionError:
error_links.append(l)
continue
if r.status_code != 200:
error_links.append(l)
continue
os.makedirs(os.path.dirname(project_path +
file_name.split("?")[0]), exist_ok=True)
with open(project_path + file_name.split("?")[0], "wb") as f:
f.write(r.text.encode('utf-8'))
f.close()
visited_links.append(l)
def save_assets(html_text):
global site_name
global project_path
global folder_name
global visited_links
global error_links
global project_name
bs = BeautifulSoup(html_text, "html.parser")
save(bs=bs, element="link", check=".css")
save(bs=bs, element="script", check=".js")
links = bs.find_all("img")
for l in links:
href = l.get("src")
if href is not None and href not in visited_links:
print("Working with : {}".format(href))
if "//" in href:
path_s = href.split("/")
file_name = ""
for i in range(3, len(path_s)):
file_name = file_name + "/" + path_s[i]
else:
file_name = href
l = site_name + file_name
try:
r = requests.get(l, stream=True)
except requests.exceptions.ConnectionError:
error_links.append(l)
continue
if r.status_code != 200:
error_links.append(l)
continue
os.makedirs(os.path.dirname(project_path +
file_name.split("?")[0]), exist_ok=True)
with open(project_path + file_name.split("?")[0], "wb") as f:
shutil.copyfileobj(r.raw, f)
visited_links.append(l)
def crawl(link):
global site_name
global folder_name
global visited_links
global error_links
global project_path
global project_name
if "http://" not in link and "https://" not in link:
link = site_name + link
if site_name in link and link not in visited_links:
print("Working with : {}".format(link))
path_s = link.split("/")
file_name = ""
for i in range(3, len(path_s)):
file_name = file_name + "/" + path_s[i]
if file_name[len(file_name) - 1] != "/":
file_name = file_name + "/"
try:
r = requests.get(link)
except requests.exceptions.ConnectionError:
print("Connection Error")
sys.exit(1)
if r.status_code != 200:
print("Invalid Response")
sys.exit(1)
print(project_path + file_name + "index.html")
os.makedirs(os.path.dirname(project_path +
file_name.split("?")[0]), exist_ok=True)
with open(project_path + file_name.split("?")[0] + "index.html", "wb") as f:
text = r.text.replace(site_name, project_name)
f.write(text.encode('utf-8'))
f.close()
visited_links.append(link)
save_assets(r.text)
soup = BeautifulSoup(r.text, "html.parser")
for link in soup.find_all('a'):
try:
crawl(link.get("href"))
except:
error_links.append(link.get("href"))
def startCrawl(url, folder="Default"):
global site_name
global folder_name
global visited_links
global error_links
global project_path
global project_name
base_dir = os.getcwd()
try:
site_name = url
project_name = folder
except IndexError:
print("Usage:\npython app.py www.example.com folder_name")
sys.exit(1)
project_path = "../" + project_name + "/"
os.makedirs(project_path, exist_ok=True)
visited_links = []
error_links = []
crawl(site_name + "/")
print("Link crawled\n")
for link in visited_links:
print("---- {}\n".format(link))
print("\n\n\nLink error\n")
for link in error_links:
print("---- {}\n".format(link))
class MyApp(QMainWindow):
def __init__(self):
super(MyApp, self).__init__()
self.ui = Ui_MainWindow()
self.ui.setupUi(self)
self.ui.submit.clicked.connect(self.passValues)
def passValues(self):
startCrawl(self.ui.url.text(), self.ui.folder.text())
if __name__ == "__main__":
app = QApplication([])
window = MyApp()
window.show()
app.exec_()
# sys.exit(app.exec_())