I'm learning Python by following Automate the Boring Stuff. This program is supposed to go to http://xkcd.com/ and download all the images for offline viewing.
I'm on version 2.7 and Mac.
For some reason, I'm getting errors like "No schema supplied" and errors with using request.get() itself.
Here is my code:
# Saves the XKCD comic page for offline read
import requests, os, bs4, shutil
url = 'http://xkcd.com/'
if os.path.isdir('xkcd') == True: # If xkcd folder already exists
shutil.rmtree('xkcd') # delete it
else: # otherwise
os.makedirs('xkcd') # Creates xkcd foulder.
while not url.endswith('#'): # If there are no more posts, it url will endswith #, exist while loop
# Download the page
print 'Downloading %s page...' % url
res = requests.get(url) # Get the page
res.raise_for_status() # Check for errors
soup = bs4.BeautifulSoup(res.text) # Dowload the page
# Find the URL of the comic image
comicElem = soup.select('#comic img') # Any #comic img it finds will be saved as a list in comicElem
if comicElem == []: # if the list is empty
print 'Couldn\'t find the image!'
else:
comicUrl = comicElem[0].get('src') # Get the first index in comicElem (the image) and save to
# comicUrl
# Download the image
print 'Downloading the %s image...' % (comicUrl)
res = requests.get(comicUrl) # Get the image. Getting something will always use requests.get()
res.raise_for_status() # Check for errors
# Save image to ./xkcd
imageFile = open(os.path.join('xkcd', os.path.basename(comicUrl)), 'wb')
for chunk in res.iter_content(10000):
imageFile.write(chunk)
imageFile.close()
# Get the Prev btn's URL
prevLink = soup.select('a[rel="prev"]')[0]
# The Previous button is first <a rel="prev" href="/1535/" accesskey="p">< Prev</a>
url = 'http://xkcd.com/' + prevLink.get('href')
# adds /1535/ to http://xkcd.com/
print 'Done!'
Here are the errors:
Traceback (most recent call last):
File "/Users/XKCD.py", line 30, in <module>
res = requests.get(comicUrl) # Get the image. Getting something will always use requests.get()
File "/Library/Python/2.7/site-packages/requests/api.py", line 69, in get
return request('get', url, params=params, **kwargs)
File "/Library/Python/2.7/site-packages/requests/api.py", line 50, in request
response = session.request(method=method, url=url, **kwargs)
File "/Library/Python/2.7/site-packages/requests/sessions.py", line 451, in request
prep = self.prepare_request(req)
File "/Library/Python/2.7/site-packages/requests/sessions.py", line 382, in prepare_request
hooks=merge_hooks(request.hooks, self.hooks),
File "/Library/Python/2.7/site-packages/requests/models.py", line 304, in prepare
self.prepare_url(url, params)
File "/Library/Python/2.7/site-packages/requests/models.py", line 362, in prepare_url
to_native_string(url, 'utf8')))
requests.exceptions.MissingSchema: Invalid URL '//imgs.xkcd.com/comics/the_martian.png': No schema supplied. Perhaps you meant http:////imgs.xkcd.com/comics/the_martian.png?
The thing is I've been reading the section in the book about the program multiple times, reading the Requests doc, as well as looking at other questions on here. My syntax looks right.
Thanks for your help!
Edit:
This didn't work:
comicUrl = ("http:"+comicElem[0].get('src'))
I thought adding the http: before would get rid of the no schema supplied error.
change your
comicUrl
to this