粘在网上刮鳕鱼

Question

我有下面的代码，我想去一个网页，把所有相关的漫画从网站上拉出来，并存储在我的电脑上。第一张图片下载很好，但似乎有一个问题，循环到网页上的前一页。如果有人能看看代码和帮助，将不胜感激。 我得到的错误是：

'Traceback (most recent call last):
  File "C:\Users\528000\Desktop\kids print\Comic-gather.py", line 41, in <module
>
    prevLink = soup.select('a[class="prevLink"]')[0]
'IndexError: list index out of range


'import requests, os, bs4
url = 'http://darklegacycomics.com'
os.makedirs('darklegacy', exist_ok=True)
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 comic image.')
else:
    try:
        comicUrl ='http://darklegacycomics.com' + comicElem[0].get('src')
        # Download the image.
        print('Downloading image %s...' % (comicUrl))
        res = requests.get(comicUrl)
        res.raise_for_status()
    except requests.exceptions.MissingSchema:
        # skip this comic
        prevLink = soup.select('.prevlink')[0]
        url = 'http://darklegacycomics.com' + prevLink.get('href')
        continue
    # Save the image to ./darklegacy.
    imageFile = open(os.path.join('darklegacy', 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[class="prevLink"]')[0]
url = 'http://darklegacycomics.com' + prevLink.get('href')''

Answer 1

这将获得所有图像：

import requests, os, bs4
from urlparse import urljoin
url = 'http://darklegacycomics.com'

soup = bs4.BeautifulSoup(requests.get(url).content)

# get all img links where src value starts with /images
links = soup.select(".comic img[src^=/image]")


for img in links:
    # extract the link
    src = img["src"]
    # use the image name as the file name
    with open(os.path.basename(src),"w") as f:
        # join the base an image url and write content to disk
        f.write(requests.get(urljoin(url, src)).content)