Last active
October 27, 2017 15:22
-
-
Save noelleleigh/7a3a30da87b592c054018136fbb59ab5 to your computer and use it in GitHub Desktop.
Python 3 script for downloading all the pages of the webcomic On a Sunbeam (http://www.onasunbeam.com/). Requires Requests (http://docs.python-requests.org/) and Beautiful Soup 4 (https://www.crummy.com/software/BeautifulSoup/).
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
'''Dowload the comic *On a Sunbeam*''' | |
import shutil | |
from urllib.parse import urljoin, urlparse | |
from os.path import basename | |
import requests | |
from bs4 import BeautifulSoup | |
def get_chapter_links(url): | |
'''Yield the links from the html at `url` that start with "chapter".''' | |
homepage_response = requests.get(url) | |
soup = BeautifulSoup(homepage_response.text, 'html.parser') | |
link_elements = soup.find_all('a') | |
for link_element in link_elements: | |
if link_element.get('href').startswith('chapter'): | |
yield urljoin(url, link_element.get('href')) | |
def get_chapter_image_links(url, homepage): | |
''' | |
Yield the urls of images from the html at `url` from the website root | |
`homepage`. | |
The images are from `<img>` elements with the class of `chapter-page` and | |
the urls are in the `data-original` attribute. | |
''' | |
chapter_response = requests.get(url) | |
soup = BeautifulSoup(chapter_response.text, 'html.parser') | |
chapter_img_elements = soup.find_all('img', class_='chapter-page') | |
for chapter_img_element in chapter_img_elements: | |
yield urljoin(homepage, chapter_img_element.get('data-original')) | |
def download_file(url, destination, log=False): | |
''' | |
Download the file at `url` to `destination`. | |
Source: https://stackoverflow.com/a/13137873 | |
''' | |
response = requests.get(url, stream=True) | |
if log: | |
print('Downloading {} to {}'.format(url, destination)) | |
if response.status_code != 200: | |
raise Exception( | |
'Request to {url} returned status code: {code} {reason}'.format( | |
url=response.url, | |
code=response.status_code, | |
reason=response.reason | |
) | |
) | |
with open(destination, 'wb') as destination_file: | |
response.raw.decode_content = True | |
shutil.copyfileobj(response.raw, destination_file) | |
def download_sunbeam(homepage): | |
''' | |
Download all the pages of *On a Sunbeam* to the current directory. | |
`homepage` is the homepage of the comic. | |
''' | |
for chapter_link in get_chapter_links(homepage): | |
for chapter_image_link in get_chapter_image_links(chapter_link, homepage): # noqa: E501 | |
filename = basename(urlparse(chapter_image_link).path) | |
download_file(chapter_image_link, filename, log=True) | |
if __name__ == '__main__': | |
download_sunbeam('http://www.onasunbeam.com/') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment