#! python3

downloadXkcd.py - Downloads every single XKCD comic.

import requests, os, 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, 'lxml')

# 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(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.')

代码是这样的，但是运行之后就是有错误，想问一下到底是哪里出错了

我觉得是不是URL不太对，报错Invalid url

显示为url错误，看了下代码。

试着改一下标红的地方，看看。

 # -*- coding: utf-8 -*-
from __future__ import unicode_literals
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, 'lxml')

    # Find the URL of the comic image.
    comicElem = soup.select('#comic img')
    if comicElem == []:
        print('Could not find 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()

        # 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.')

res = requests.get(comicUrl)‘

这里出错了
comicUrl 你打印出来看看
这个图片的地址应该是不完整的 需要进行处理为正常的格式