/
first.py
executable file
·79 lines (47 loc) · 1.75 KB
/
first.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
#!/usr/bin/env python
import requests
from bs4 import BeautifulSoup
web_base="https://web.totsrucs.cat/"
URL = web_base+"index.php?pagina=infantil&ind=Tots"
page = requests.get(URL)
soup = BeautifulSoup(page.content, "html.parser")
results= soup.find(id="llista_elinks")
#print(results.prettify())
urls = results.findAll('a', href=True)
for line in urls:
try:
href=line['href']
URL2=web_base+href
page2 = requests.get(URL2)
soup2 = BeautifulSoup(page2.content, "html.parser")
results2= soup2.find(id="contingut")
urls2 = results2.findAll('a', href=True)
for line2 in urls2:
try:
href2=line2['href']
URL3=web_base+href2
page3 = requests.get(URL3)
soup3 = BeautifulSoup(page3.content, "html.parser")
results3= soup3.find_all("td",{"class":"nom"})
for resultline in results3:
urls3 = resultline.findAll('a', href=True)
for line3 in urls3:
try:
href3=line3['href']
URL4=web_base+href3
page4 = requests.get(URL4)
soup4 = BeautifulSoup(page4.content, "html.parser")
results4= soup4.find(id="contingut")
urls4 = results4.findAll('a', href=True)
for i in urls4:
print(line.text+"@@@"+line2.text+"@@@"+line3.text+"@@@"+i.text+"@@@@"+i['href'])
except Exception as e:
print(e)
pass
except Exception as e:
print(e)
pass
except Exception as e:
print(e)
pass
print("Finished")