crtxcr/looqs
1
0
Fork 0
Code Issues Pull Requests 1 Releases Wiki Activity

remove pdf_pagecount()

Browse Source
This commit is contained in:
Albert S. 2018-08-09 23:00:44 +02:00
parent 07b3479029
commit e006a95673
1 changed files with 2 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
addindex
View File

@ -41,11 +41,8 @@ def strip_irrelevant(content):
result = re.sub(' +', ' ', result) result = re.sub(' +', ' ', result)
return result; return result;
def pdf_pagecount(path):
cmd = "pdfinfo " + path + " | grep Pages | awk '{print $2}'"
stdout,stderr = subprocess.Popen(cmd,shell=True,stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
result = int(stdout)
return result
def process_pdf(path): def process_pdf(path):
result = list() result = list()
args=["pdftotext", path, "-"] args=["pdftotext", path, "-"]