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

fix title encoding for another pdf case

Browse Source
This commit is contained in:
Bryan Bishop 2013-01-16 02:25:04 -06:00
parent 723b9f18d7
commit b1dcaf0e23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
modules/papers.py
View File

@ -159,9 +159,10 @@ def download_url(url):
# extract some metadata with xpaths # extract some metadata with xpaths
citation_pdf_url = find_citation_pdf_url(tree, url) citation_pdf_url = find_citation_pdf_url(tree, url)
citation_title = find_citation_title(tree) citation_title = find_citation_title(tree)
citation_title = citation_title.encode("ascii", "ignore")
if citation_pdf_url and citation_title: if citation_pdf_url and citation_title:
response = requests.get(citation_pdf_url, headers={"User-Agent": "gundam-gdf"}) response = requests.get(citation_pdf_url, headers={"User-Agent": "pdf-defense-force"})
content = response.content content = response.content
if "pdf" in response.headers["content-type"]: if "pdf" in response.headers["content-type"]:
extension = ".pdf" extension = ".pdf"