forked from chenguohui/AutomatePython
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdownloadXkcd.py
More file actions
37 lines (30 loc) · 1.12 KB
/
downloadXkcd.py
File metadata and controls
37 lines (30 loc) · 1.12 KB
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
#! python3
# downloadXkcd.py - Downloads every single XKCD comic.
import requests, os, bs4
url = 'https://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, 'html.parser')
# Find the URL of the comic image.
comicElem = soup.select('#comic img')
if comicElem == []:
print('Could not find comic image.')
else:
comicUrl = comicElem[0].get('src')
# Download the image.
print('Downloading image %s...' % (comicUrl))
res = requests.get(str('http:' + comicUrl))
res.raise_for_status()
# Save the image to ./xkcd
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.')