mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2023-12-21 10:23:01 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3 from I-Al-Istannen/master

Browse Source 
Download all TGI files and not just lectures
This commit is contained in:
Garmelon 2019-10-17 21:10:21 +00:00 committed by GitHub
commit 1f5475abc5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
PFERD/tgi.py
View File

@ -18,7 +18,6 @@ pretty = PrettyLogger(logger)
class TGI: class TGI:
CRAWL_URL = "https://i11www.iti.kit.edu/teaching/{year}/tgi/index" CRAWL_URL = "https://i11www.iti.kit.edu/teaching/{year}/tgi/index"
BASE_URL = "https://i11www.iti.kit.edu" BASE_URL = "https://i11www.iti.kit.edu"
LINK_RE = re.compile(r"^/_media/teaching/.*?/(tgi-\d+-\d+-)([^/]*\.pdf)$")
def __init__(self, base_path, year="winter2019"): def __init__(self, base_path, year="winter2019"):
self.base_path = base_path self.base_path = base_path
@ -49,11 +48,11 @@ class TGI:
files = [] files = []
for found in soup.find_all("a", href=self.LINK_RE): for found in soup.select("a.mediafile.mf_pdf"):
url = found["href"] url = found["href"]
full_url = self.BASE_URL + url full_url = self.BASE_URL + url
filename = re.search(self.LINK_RE, url).group(2) filename = re.search(r"\d+(/tgi)?/(.+.pdf)", url).group(2)
path = pathlib.PurePath(filename) path = pathlib.PurePath(filename)
logger.debug(f"Found file {filename} at {full_url}") logger.debug(f"Found file {filename} at {full_url}")