Skip to content
This repository was archived by the owner on Dec 22, 2023. It is now read-only.

Commit ffb9ca9

Browse files
AdityaJ7AdityaJ7
authored
Merge pull request #453 from kartavyashankar/kartavyashankar
Scrapping News from Google News
2 parents fb1d464 + a6da906 commit ffb9ca9

File tree

5 files changed

+268
-0
lines changed

5 files changed

+268
-0
lines changed

‎Scripts/Web_Scrappers/google_news_(ui_based)/README.md‎

Lines changed: 27 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,27 @@
1+
# Google News - Latest News from all over world (involves user interaction)
2+
3+
Scrapes the google news website and stores the latest World News in `world_news.txt` file and user defined custom news set in `custom_news.txt`.
4+
5+
## Pre-Requisites
6+
7+
Run The Command `pip install -r requirements.txt`
8+
9+
## To Run the File
10+
11+
For Windows - `python main.py`
12+
13+
For Ubuntu/Linux - `python3 main.py`
14+
15+
## Screenshots -
16+
17+
### Screenshot of the generated `world_news.txt` file
18+
19+
![Screenshot](image1.png)
20+
21+
### Screenshot of the generated `custom_news.txt` file
22+
23+
![Screenshot](image2.png)
24+
25+
## *Author Name*
26+
27+
[Kartavya Shankar](https://github.com/kartavyashankar)

‎Scripts/Web_Scrappers/google_news_(ui_based)/image1.png‎

300 KB
Loading

‎Scripts/Web_Scrappers/google_news_(ui_based)/image2.png‎

304 KB
Loading

‎Scripts/Web_Scrappers/google_news_(ui_based)/main.py‎

Lines changed: 238 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,238 @@
1+
import requests as rq
2+
import re
3+
from bs4 import BeautifulSoup
4+
5+
def fetch_news(link, file_name='custom_news.txt'):
6+
header = {'User-Agent' : 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}
7+
r = rq.get(link, headers=header)
8+
soup = BeautifulSoup(r.content, 'html.parser')
9+
main_div = soup.find("div", attrs={'class' : re.compile("lBwEZb BL5WZb GndZbb")})
10+
news_set = main_div.find_all('div', attrs={'jscontroller' : re.compile("d0DtYd")})
11+
news_set2 = main_div.find_all('div', attrs={'class' : re.compile("xrnccd")})
12+
sources = []
13+
links = []
14+
headings = []
15+
for s in news_set:
16+
source = s.find("a", attrs={'class' : re.compile("wEwyrc AVN2gc uQIVzc Sksgp")})
17+
time = s.find('time', attrs={'class' : re.compile("WW6dff uQIVzc Sksgp")})
18+
try:
19+
stri = source.text+", Uploaded - "+time.text
20+
except AttributeError:
21+
stri = source.text
22+
sources.append(stri)
23+
link = s.find('a')
24+
links.append("https://news.google.com"+link['href'][1:])
25+
head = s.find('h3')
26+
headings.append(head.text)
27+
for s in news_set2:
28+
headings.append(s.h3.text)
29+
links.append("https://news.google.com"+s.a['href'][1:])
30+
time = s.find('time', attrs={'class' : re.compile("WW6dff uQIVzc Sksgp")})
31+
source = s.find("a", attrs={'class' : re.compile("wEwyrc AVN2gc uQIVzc Sksgp")})
32+
try:
33+
stri = source.text+", Uploaded - "+time.text
34+
except AttributeError:
35+
stri = source.text
36+
sources.append(stri)
37+
l = len(headings)
38+
with open(file_name, "w") as file:
39+
for i in range(l):
40+
file.write(sources[i]+'\n')
41+
file.write(headings[i]+'\n')
42+
file.write("Ref: "+links[i]+'\n\n')
43+
file.close()
44+
if(file_name=='custom_news.txt'):
45+
print('Your news in ready in "custom_news.txt" file.')
46+
47+
ans = input("Do you want to fetch latest World News (y/n) ? ")
48+
if(ans=='y'):
49+
print('Fetching World News... This might take a while')
50+
fetch_news('https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx1YlY4U0FtVnVHZ0pKVGlnQVAB?hl=en-IN&gl=IN&ceid=IN%3Aen', 'world_news.txt')
51+
print('Done!!')
52+
print('World latest news can be found in "world_news.txt" file.')
53+
54+
print('You can also grab custom news of your taste :-)')
55+
print('\t 1. Business')
56+
print('\t 2. Technology')
57+
print('\t 3. Entertainment')
58+
print('\t 4. Sports')
59+
print('\t 5. Science')
60+
print('\t 6. Health')
61+
c1=True
62+
c2=True
63+
ch = int(input('Enter your choice (Eg : 1 for Business): '))
64+
print('')
65+
66+
fetch = ""
67+
if(ch==1):
68+
print('Enter the sub-topic of the category you selected. You can choose from :')
69+
print('\t a. Latest')
70+
print('\t b. Economy')
71+
print('\t c. Markets')
72+
print('\t d. Jobs')
73+
print('\t e. Personal finance')
74+
print('\t f. Enterpreneurship')
75+
ch2=input('Enter your choice (Eg : a for Latest): ')
76+
if(ch2=='a'):
77+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx6TVdZU0FtVnVHZ0pKVGlnQVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
78+
elif(ch2=='b'):
79+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx6TVdZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTENCQVNNd29JTDIwdk1EbHpNV1lTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1HZG1jSE16S2dzU0NTOXRMekJuWm5Cek15Z0EqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURsek1XWVNCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
80+
elif(ch2=='c'):
81+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx6TVdZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiYENCQVNRZ29JTDIwdk1EbHpNV1lTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1EbDVOSEJ0S2hvS0dBb1VUVUZTUzBWVVUxOVRSVU5VU1U5T1gwNUJUVVVnQVNnQSouCAAqKggKIiRDQkFTRlFvSUwyMHZNRGx6TVdZU0JXVnVMVWRDR2dKSlRpZ0FQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
82+
elif(ch2=='d'):
83+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx6TVdZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiXENCQVNQd29JTDIwdk1EbHpNV1lTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1ERjBjWEpyS2hjS0ZRb1JTazlDVTE5VFJVTlVTVTlPWDA1QlRVVWdBU2dBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EbHpNV1lTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
84+
elif(ch2=='e'):
85+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx6TVdZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTENCQVNNd29JTDIwdk1EbHpNV1lTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1ERjVObU54S2dzU0NTOXRMekF4ZVRaamNTZ0EqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURsek1XWVNCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
86+
elif(ch2=='f'):
87+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx6TVdZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1EbHpNV1lTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ESnVkM0VxQ2hJSUwyMHZNREp1ZDNFb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EbHpNV1lTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
88+
else:
89+
print('Invalid Choice!')
90+
c2=False
91+
elif(ch==2):
92+
print('Enter the sub-topic of the category you selected. You can choose from :')
93+
print('\t a. Latest')
94+
print('\t b. Mobile')
95+
print('\t c. Gadgets')
96+
print('\t d. Internet')
97+
print('\t e. Virtual reality')
98+
print('\t f. Artificial intelligence')
99+
print('\t g. Computing')
100+
ch2=input('Enter your choice (Eg : a for Latest): ')
101+
if(ch2=='a'):
102+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pKVGlnQVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
103+
elif(ch2=='b'):
104+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiZkNCQVNSZ29JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1EVXdhemdxSHdvZENobE5UMEpKVEVWZlVFaFBUa1ZmVTBWRFZFbFBUbDlPUVUxRklBRW9BQSouCAAqKggKIiRDQkFTRlFvSUwyMHZNRGRqTVhZU0JXVnVMVWRDR2dKSlRpZ0FQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
105+
elif(ch2=='c'):
106+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiX0NCQVNRUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1ESnRaakZ1S2hrS0Z3b1RSMEZFUjBWVVgxTkZRMVJKVDA1ZlRrRk5SU0FCS0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
107+
elif(ch2=='d'):
108+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ETnliSFFxQ2hJSUwyMHZNRE55YkhRb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
109+
elif(ch2=='e'):
110+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1EZGZibmtxQ2hJSUwyMHZNRGRmYm5rb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
111+
elif(ch2=='f'):
112+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiR0NCQVNMd29JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlJTkNBUWFDUW9ITDIwdk1HMXJlaW9KRWdjdmJTOHdiV3Q2S0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
113+
elif(ch2=='g'):
114+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ERnNjSE1xQ2hJSUwyMHZNREZzY0hNb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EZGpNWFlTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
115+
else:
116+
print('Invalid Choice!')
117+
c2=False
118+
elif(ch==3):
119+
print('Enter the sub-topic of the category you selected. You can choose from :')
120+
print('\t a. Latest')
121+
print('\t b. Movies')
122+
print('\t c. Music')
123+
print('\t d. TV')
124+
print('\t e. Books')
125+
print('\t f. Art')
126+
print('\t g. Celebrities')
127+
ch2=input('Enter your choice (Eg : a for Latest): ')
128+
if(ch2=='a'):
129+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNREpxYW5RU0FtVnVHZ0pKVGlnQVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
130+
elif(ch2=='b'):
131+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNREpxYW5RU0FtVnVHZ0pKVGlnQVAB/sections/CAQiXkNCQVNRQW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ESjJlRzRxR1FvWENoTk5UMVpKUlZOZlUwVkRWRWxQVGw5T1FVMUZJQUVvQUEqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURKcWFuUVNCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
132+
elif(ch2=='c'):
133+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNREpxYW5RU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1EUnliR1lxQ2hJSUwyMHZNRFJ5YkdZb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
134+
elif(ch2=='d'):
135+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNREpxYW5RU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1EZGpOVElxQ2hJSUwyMHZNRGRqTlRJb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
136+
elif(ch2=='e'):
137+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNREpxYW5RU0FtVnVHZ0pKVGlnQVAB/sections/CAQiXkNCQVNRQW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1HSjBYMk16S2hnS0Znb1NRazlQUzFOZlUwVkRWRWxQVGw5T1FVMUZJQUVvQUEqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURKcWFuUVNCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
138+
elif(ch2=='f'):
139+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNREpxYW5RU0FtVnVHZ0pKVGlnQVAB/sections/CAQiR0NCQVNMd29JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlJTkNBUWFDUW9ITDIwdk1HcHFkeW9KRWdjdmJTOHdhbXAzS0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
140+
elif(ch2=='g'):
141+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNREpxYW5RU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ERnlabm9xQ2hJSUwyMHZNREZ5Wm5vb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1ESnFhblFTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
142+
else:
143+
print('Invalid Choice!')
144+
c2=False
145+
elif(ch==4):
146+
print('Enter the sub-topic of the category you selected. You can choose from :')
147+
print('\t a. Latest')
148+
print('\t b. Cricket')
149+
print('\t c. Hockey')
150+
print('\t d. Tennis')
151+
print('\t e. Football')
152+
print('\t f. Badminton')
153+
print('\t g. Kabbadi')
154+
print("\t h. Women's Cricket")
155+
print("\t i. Basketball")
156+
print('\t j. F1 Racing')
157+
ch2=input('Enter your choice (Eg : a for Latest): ')
158+
if(ch2=='a'):
159+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
160+
elif(ch2=='b'):
161+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTENCQVNNd29JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1ESTBibW94S2dzS0NSSUhRM0pwWTJ0bGRDZ0EqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURadWRHb1NCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
162+
elif(ch2=='c'):
163+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTkNCQVNOQW9JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJUkNBUWFEUW9MTDIwdk1ERXhZbUk0TWpNcUNnb0lFZ1pJYjJOclpYa29BQSouCAAqKggKIiRDQkFTRlFvSUwyMHZNRFp1ZEdvU0JXVnVMVWRDR2dKSlRpZ0FQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
164+
elif(ch2=='d'):
165+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1EZGljekFxQ2dvSUVnWlVaVzV1YVhNb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
166+
elif(ch2=='e'):
167+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTENCQVNNd29JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ESjJlRFFxREFvS0VnaEdiMjkwWW1Gc2JDZ0EqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURadWRHb1NCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
168+
elif(ch2=='f'):
169+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTkNCQVNOQW9JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ERTVOR1FxRFFvTEVnbENZV1J0YVc1MGIyNG9BQSouCAAqKggKIiRDQkFTRlFvSUwyMHZNRFp1ZEdvU0JXVnVMVWRDR2dKSlRpZ0FQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
170+
elif(ch2=='g'):
171+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiS0NCQVNNZ29JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1EUmlNSE1xQ3dvSkVnZExZV0ppWVdScEtBQSouCAAqKggKIiRDQkFTRlFvSUwyMHZNRFp1ZEdvU0JXVnVMVWRDR2dKSlRpZ0FQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
172+
elif(ch2=='h'):
173+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiV0NCQVNPd29JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1EY3diV3M0S2hNS0VSSVBWMjl0Wlc0bmN5QkRjbWxqYTJWMEtBQSouCAAqKggKIiRDQkFTRlFvSUwyMHZNRFp1ZEdvU0JXVnVMVWRDR2dKSlRpZ0FQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
174+
elif(ch2=='i'):
175+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiT0NCQVNOUW9JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ERTRkemdxRGdvTUVncENZWE5yWlhSaVlXeHNLQUEqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURadWRHb1NCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
176+
elif(ch2=='j'):
177+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp1ZEdvU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTkNCQVNOQW9JTDIwdk1EWnVkR29TQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ESjRlaklxRFFvTEVnbEdNU0JTWVdOcGJtY29BQSouCAAqKggKIiRDQkFTRlFvSUwyMHZNRFp1ZEdvU0JXVnVMVWRDR2dKSlRpZ0FQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
178+
else:
179+
print('Invalid Choice!')
180+
c2=False
181+
elif(ch==5):
182+
print('Enter the sub-topic of the category you selected. You can choose from :')
183+
print('\t a. Latest')
184+
print('\t b. Environment')
185+
print('\t c. Outer space')
186+
print('\t d. Physics')
187+
print('\t e. Genetics')
188+
print('\t f. Wildlife')
189+
ch2=input('Enter your choice (Eg : a for Latest): ')
190+
if(ch2=='a'):
191+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp0Y1RjU0FtVnVHZ0pKVGlnQVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
192+
elif(ch2=='b'):
193+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp0Y1RjU0FtVnVHZ0pKVGlnQVAB/sections/CAQiT0NCQVNOUW9JTDIwdk1EWnRjVGNTQldWdUxVZENHZ0pKVGlJUUNBUWFEQW9LTDIwdk1EUTJOak15Y3lvTUVnb3ZiUzh3TkRZMk16SnpLQUEqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURadGNUY1NCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
194+
elif(ch2=='c'):
195+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp0Y1RjU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTENCQVNNd29JTDIwdk1EWnRjVGNTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1ERTRNek4zS2dzU0NTOXRMekF4T0RNemR5Z0EqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURadGNUY1NCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
196+
elif(ch2=='d'):
197+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp0Y1RjU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1EWnRjVGNTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1EVnhhblFxQ2hJSUwyMHZNRFZ4YW5Rb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EWnRjVGNTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
198+
elif(ch2=='e'):
199+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp0Y1RjU0FtVnVHZ0pKVGlnQVAB/sections/CAQiSkNCQVNNUW9JTDIwdk1EWnRjVGNTQldWdUxVZENHZ0pKVGlJT0NBUWFDZ29JTDIwdk1ETTJYeklxQ2hJSUwyMHZNRE0yWHpJb0FBKi4IACoqCAoiJENCQVNGUW9JTDIwdk1EWnRjVGNTQldWdUxVZENHZ0pKVGlnQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
200+
elif(ch2=='f'):
201+
fetch='https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRFp0Y1RjU0FtVnVHZ0pKVGlnQVAB/sections/CAQiTENCQVNNd29JTDIwdk1EWnRjVGNTQldWdUxVZENHZ0pKVGlJUENBUWFDd29KTDIwdk1ERXlPREJuS2dzU0NTOXRMekF4TWpnd1p5Z0EqLggAKioICiIkQ0JBU0ZRb0lMMjB2TURadGNUY1NCV1Z1TFVkQ0dnSkpUaWdBUAFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
202+
else:
203+
print('Invalid Choice!')
204+
c2=False
205+
elif(ch==6):
206+
print('Enter the sub-topic of the category you selected. You can choose from :')
207+
print('\t a. Latest')
208+
print('\t b. Medicine')
209+
print('\t c. Healthcare')
210+
print('\t d. Mental health')
211+
print('\t e. Nutrition')
212+
print('\t f. Fitness')
213+
ch2=input('Enter your choice (Eg : a for Latest): ')
214+
if(ch2=='a'):
215+
fetch='https://news.google.com/topics/CAAqIQgKIhtDQkFTRGdvSUwyMHZNR3QwTlRFU0FtVnVLQUFQAQ?hl=en-IN&gl=IN&ceid=IN%3Aen'
216+
elif(ch2=='b'):
217+
fetch='https://news.google.com/topics/CAAqIQgKIhtDQkFTRGdvSUwyMHZNR3QwTlRFU0FtVnVLQUFQAQ/sections/CAQiRENCQVNMUW9JTDIwdk1HdDBOVEVTQldWdUxVZENJZzRJQkJvS0NnZ3ZiUzh3TkhOb015b0tFZ2d2YlM4d05ITm9NeWdBKikIAColCAoiH0NCQVNFUW9JTDIwdk1HdDBOVEVTQldWdUxVZENLQUFQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
218+
elif(ch2=='c'):
219+
fetch='https://news.google.com/topics/CAAqIQgKIhtDQkFTRGdvSUwyMHZNR3QwTlRFU0FtVnVLQUFQAQ/sections/CAQiR0NCQVNMd29JTDIwdk1HdDBOVEVTQldWdUxVZENJZzhJQkJvTENna3ZiUzh3TVcxM01uZ3FDeElKTDIwdk1ERnRkeko0S0FBKikIAColCAoiH0NCQVNFUW9JTDIwdk1HdDBOVEVTQldWdUxVZENLQUFQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
220+
elif(ch2=='d'):
221+
fetch='https://news.google.com/topics/CAAqIQgKIhtDQkFTRGdvSUwyMHZNR3QwTlRFU0FtVnVLQUFQAQ/sections/CAQiR0NCQVNMd29JTDIwdk1HdDBOVEVTQldWdUxVZENJZzhJQkJvTENna3ZiUzh3TTNnMk9XY3FDeElKTDIwdk1ETjROamxuS0FBKikIAColCAoiH0NCQVNFUW9JTDIwdk1HdDBOVEVTQldWdUxVZENLQUFQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
222+
elif(ch2=='e'):
223+
fetch='https://news.google.com/topics/CAAqIQgKIhtDQkFTRGdvSUwyMHZNR3QwTlRFU0FtVnVLQUFQAQ/sections/CAQiRENCQVNMUW9JTDIwdk1HdDBOVEVTQldWdUxVZENJZzRJQkJvS0NnZ3ZiUzh3TldScVl5b0tFZ2d2YlM4d05XUnFZeWdBKikIAColCAoiH0NCQVNFUW9JTDIwdk1HdDBOVEVTQldWdUxVZENLQUFQAVAB?hl=en-IN&gl=IN&ceid=IN%3Aen'
224+
elif(ch2=='f'):
225+
fetch='https://news.google.com/topics/CAAqIQgKIhtDQkFTRGdvSUwyMHZNR3QwTlRFU0FtVnVLQUFQAQ/sections/CAQiW0NCQVNQZ29JTDIwdk1HdDBOVEVTQldWdUxVZENJZzhJQkJvTENna3ZiUzh3TWpkNE4yNHFHZ29ZQ2hSR1NWUk9SVk5UWDFORlExUkpUMDVmVGtGTlJTQUJLQUEqKQgAKiUICiIfQ0JBU0VRb0lMMjB2TUd0ME5URVNCV1Z1TFVkQ0tBQVABUAE?hl=en-IN&gl=IN&ceid=IN%3Aen'
226+
else:
227+
print('Invalid Choice!')
228+
c2=False
229+
else:
230+
c1=False
231+
print('')
232+
cond = c1 & c2
233+
if cond is True:
234+
print('Fetching your custom News...')
235+
fetch_news(link=fetch)
236+
print('Thank You')
237+
else:
238+
print('The program will now exit!')

‎Scripts/Web_Scrappers/google_news_(ui_based)/requirements.txt‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
beautifulsoup4==4.8.2
2+
requests==2.22.0
3+
requests-html==0.10.0

0 commit comments

Comments
 (0)