blob: 11f7f6bbaa62f9e98e513ebaf4a5336ddee13cad (
plain)
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
|
#!/usr/bin/env python3
#Chapter 11 Project
#XKCD Comic Download - Downloads every XKCD comic
import requests
import os
import bs4
url = 'http://xkcd.com' #Starting url
os.makedirs('xkcd', exist_ok=True) #Store comics in ./xkcd
while not url.endswith('#'):
#Download the page
print('Downloading page %s...' % url)
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text)
comicElem = soup.select('#comic img')
if comicElem == []:
print('Could not find the comic image.')
else:
comicUrl = 'http:' + comicElem[0].get('src')
# Download the image
print('Downloading image %s...' % (comicUrl))
res = requests.get(comicUrl)
res.raise_for_status()
imageFile = open(os.path.join('xkcd', os.path.basename(comicUrl)), 'wb')
for chunk in res.iter_content(100000):
imageFile.write(chunk)
imageFile.close()
#Get the Prev button's url.
prevLink = soup.select('a[rel="prev"]')[0]
url = 'http://xkcd.com' + prevLink.get('href')
print('Done.')
|
