blob: ade7e18187f65818ff7a30a83c2d83a9c2a4e2f8 (
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
39
40
41
42
|
#! /usr/bin/env python3
# Chapter 15 Project Multithreaded XKCD Downloader
import threading
import os
import bs4
import requests
os.makedirs('xkcd', exist_ok=True)
def downloadXkcd(startComic, endComic):
for urlNumber in range(startComic, endComic):
print('Downloading page http://xkcd.com/%s...' % (urlNumber))
res = requests.get('http://xkcd.com/%s' % (urlNumber))
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text)
comicElem = soup.select('#comic img')
if comicElem == []:
print('Could not find comic image.')
else:
comicUrl = comicElem[0].get('src')
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.inter_content(100000):
imageFile.write(chunk)
imageFile.close()
downloadThreads = []
for i in range(0, 1400, 100):
downloadThread = threading.Thread(target=downloadXkcd, args=(i, i +90))
downloadThreads.append(downloadThread)
downloadThread.start()
for downloadThread in downloadThreads:
downloadThread.join()
print('Done.')
|
