Created
March 2, 2016 08:03
-
-
Save fpom/ef83e95afa71605c71b7 to your computer and use it in GitHub Desktop.
Get links from The David W. Niven Collection of Early Jazz Legends
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
| # this is for Python 2.x | |
| import urlparse | |
| from pyquery import PyQuery as pq | |
| url = "https://archive.org/details/davidwnivenjazz" | |
| doc = pq(url) | |
| todo = [] | |
| for a in doc("a[href]") : | |
| href = a.attrib["href"] | |
| if not href.startswith("/details/") or href.startswith("/details/davidwnivenjazz") : | |
| continue | |
| todo.append(urlparse.urljoin(url, href)) | |
| for link in todo : | |
| print "#", link | |
| doc = pq(link) | |
| for a in doc("a.hover-badge") : | |
| href = a.attrib["href"] | |
| if "/formats=" in href : | |
| continue | |
| path = href.split("/")[-1] | |
| print "wget --continue -O 'dl/%s.zip' '%s'" % (path, urlparse.urljoin(url, href)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment