def rename_file(pdf, bibitem):
"""Attempt to rename pdf according to bibitem."""
year = _get_bib_element(bibitem, "year")
author = _get_bib_element(bibitem, "author")
if author:
author = author.split(",")[0].replace(' ', '')
title = _get_bib_element(bibitem, "title")
# pick one word for the title
title = title.strip().split()[0]
filename = secure_filename('%s%s%s.pdf' % (author, year[-2:], title))
newfile = pdf.replace(os.path.basename(pdf), filename)
print
print "Will rename:"
print
print " %s" % pdf
print
print "to"
print
print " %s" % newfile
print
print "Proceed? [y/N]"
answer = raw_input()
if answer == 'y':
print "Renaming %s to %s" % (pdf, newfile)
os.rename(pdf, newfile)
else:
print "Aborting."
def download(url, usecache=True, cached=None, cachedir='cache~/', cachedonly=False, **opts):
"""
Download (or cache) ``url`` to file. On success: return file name of stored
contents. Upon failure: return None.
Will retry ``tries`` times with ``pause`` seconds between each attempt to
download.
Download will timeout after ``timeout`` seconds.
If ``cachedonly`` is enabled, this function will not download anything. It
will simply return the cached filename if it exists.
"""
if not cached:
if cachedir:
mkdir(cachedir)
cached = os.path.join(cachedir, secure_filename(url))
else:
assert not usecache, 'must specify cachedir'
# only return something for cached files
if cachedonly and not os.path.exists(cached):
return
if usecache and os.path.exists(cached):
return cached
# use wget for ftp files
if url.startswith('ftp'):
return wget(url, cached)
if url.startswith('http'):
return robust_download(url, cached, **opts)
def cache_document(src, dest=None):
"Cache a document, return filename of the dest file."
# TODO: use a staging area in case something breaks in the middle of adding.
src = Path(src)
if dest is None:
# Find a reasonable filename if dest isn't specified
if is_url(src):
dest = CACHE / secure_filename(src)
else:
dest = CACHE / src.basename()
else:
dest = CACHE / dest
if dest.exists():
# TODO: Suggest update methods or renaming the file
raise SkidFileExists(dest)
if is_url(src):
cache_url(src, dest)
elif src.exists(): # is this something on disk?
src.copy2(dest)
print('copy:', src, '->', dest)
else:
raise SkidError(
"cache_document doesn't know what to do with source %r\n"
"Trying to add a nonexistent file?" % str(src))
return dest
def cache_document(src, dest=None):
"Cache a document, return filename of the dest file."
# TODO: use a staging area in case something breaks in the middle of adding.
src = path(src)
if dest is None:
# Find a reasonable filename if dest isn't specified
if is_url(src):
dest = CACHE / secure_filename(src)
else:
dest = CACHE / src.basename()
else:
dest = CACHE / dest
if dest.exists():
# TODO: Suggest update methods or renaming the file
raise SkidFileExists(dest)
if is_url(src):
cache_url(src, dest)
elif src.exists(): # is this something on disk?
src.copy2(dest)
print 'copy:', src, '->', dest
else:
raise SkidError("cache_document doesn't know what to do with source %r\n"
"Trying to add a nonexistent file?" % str(src))
return dest
def rename_file(pdf, bibitem):
"""Attempt to rename pdf according to bibitem."""
year = _get_bib_element(bibitem, "year")
author = _get_bib_element(bibitem, "author")
if author:
author = author.split(",")[0].replace(' ','')
title = _get_bib_element(bibitem, "title")
# pick one word for the title
title = title.strip().split()[0]
filename = secure_filename('%s%s%s.pdf' % (author, year[-2:], title))
newfile = pdf.replace(os.path.basename(pdf), filename)
print
print "Will rename:"
print
print " %s" % pdf
print
print "to"
print
print " %s" % newfile
print
print "Proceed? [y/N]"
answer = raw_input()
if answer == 'y':
print "Renaming %s to %s" % (pdf, newfile)
os.rename(pdf, newfile)
else:
print "Aborting."
def cache_url(url):
"""
Download url, write contents to file. Return filename of contents, None on
failure to download.
"""
cached = CACHE / secure_filename(url)
assert not cached.exists(), 'File %s already exists.' % cached
# TODO: we should tell download where to store stuff explicitly... right now
# we just both have the same convention.
if not download(url, timeout=60, usecache=False, cached=cached):
raise Exception('Failed to download %s.' % url)
return cached
def download(url,
usecache=True,
cached=None,
cachedir='cache~/',
cachedonly=False,
**opts):
"""
Download (or cache) ``url`` to file. On success: return file name of stored
contents. Upon failure: return None.
Will retry ``tries`` times with ``pause`` seconds between each attempt to
download.
Download will timeout after ``timeout`` seconds.
If ``cachedonly`` is enabled, this function will not download anything. It
will simply return the cached filename if it exists.
"""
if not cached:
if cachedir:
mkdir(cachedir)
cached = os.path.join(cachedir, secure_filename(url))
else:
assert not usecache, 'must specify cachedir'
# only return something for cached files
if cachedonly and not os.path.exists(cached):
return
if usecache and os.path.exists(cached):
return cached
# use wget for ftp files
if url.startswith('ftp'):
return wget(url, cached)
if url.startswith('http'):
return robust_download(url, cached, **opts)
