phyks/bmc
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

use pdfparanoia to remove watermarks

Browse Source
This commit is contained in:
Bryan Bishop 2013-02-09 07:41:50 -06:00
parent bef66e1241
commit 357e268e96
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
modules/papers.py
View File

@ -9,6 +9,8 @@ import requests
import lxml.etree import lxml.etree
from StringIO import StringIO from StringIO import StringIO
import pdfparanoia
def download(phenny, input, verbose=True): def download(phenny, input, verbose=True):
""" """
Downloads a paper. Downloads a paper.
@ -202,6 +204,7 @@ def download_url(url):
new_response = requests.get(pdf_url, headers={"User-Agent": "time-machine/1.0"}) new_response = requests.get(pdf_url, headers={"User-Agent": "time-machine/1.0"})
new_content = new_response.content new_content = new_response.content
if "pdf" in new_response.headers["content-type"]: if "pdf" in new_response.headers["content-type"]:
new_content = pdfparanoia.scrub(new_content)
extension = ".pdf" extension = ".pdf"
except Exception: except Exception:
pass pass
@ -244,6 +247,9 @@ def download_url(url):
path = os.path.join("/home/bryan/public_html/papers2/paperbot/", title + extension) path = os.path.join("/home/bryan/public_html/papers2/paperbot/", title + extension)
if extension in [".pdf", "pdf"]:
content = pdfparanoia.scrub(content)
file_handler = open(path, "w") file_handler = open(path, "w")
file_handler.write(content) file_handler.write(content)
file_handler.close() file_handler.close()