String Theory Wiki - User contributions [en]

Arxiv.py

2010-04-10T01:55:44Z

Newacct:

Copy the following text into a file called arxiv.py with your favourite text editor
<pre>
#! /usr/bin/python

## arXiv script version 0.2

## Copyright 2008 Tom Brown

## This program is free software; you can redistribute it and/or
## modify it under the terms of the GNU General Public License as
## published by the Free Software Foundation; either version 3 of the
## License, or (at your option) any later version.

## This program is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.

## You should have received a copy of the GNU General Public License
## along with this program. If not, see <http://www.gnu.org/licenses/>.

## See http://www.stringwiki.org/wiki/ArXiv_script for more usage
## instructions

'''arXiv script
Usage:
python arxiv.py reference [ -htabcjdps ] [ --help ]
"reference" must be a standard arXiv reference, e.g. hep-th/9711200, 0705.0303.
Options:
-h, --help
displays this help message
-t
displays the title
-a
displays the author(s)
-b
displays the aBstract
-c
displays the comments
-j
displays the journal reference
-d
downloads the PDF
-p
downloads the PS
-s
downloads the source file
'''

__version__ = "0.2"
__author__ = "Tom Brown"
__copyright__ = "Copyright 2008 Tom Brown, GNU GPL 3"

import sys, os, getopt, re, urllib,gzip

def findRefType(ref):
ref = ref.replace('arxiv:','')
if re.search(r'^[a-zA-Z\-]+/\d{7}$',ref):
type = 'old-style eprint'
elif re.search(r'^\d{7}$',ref):
type = 'old-style eprint'
ref = 'hep-th/' + ref
elif re.search('^\d{4}\.\d{4}$',ref):
type = 'new-style eprint'
else:
type = 'not arXiv'

return type, ref

def downloadPDF(ref,type,downloadPath):
downloadPath = os.path.expanduser(downloadPath)
if type == 'old-style eprint':
urllib.urlretrieve('http://arxiv.org/pdf/' + ref, downloadPath + ref.replace('/','-') + '.pdf')
elif type == 'new-style eprint':
urllib.urlretrieve('http://arxiv.org/pdf/' + ref, downloadPath + ref + '.pdf')

def downloadPS(ref,type,downloadPath):
downloadPath = os.path.expanduser(downloadPath)
filename = downloadPath + ref.replace('/','-')
urllib.urlretrieve('http://arxiv.org/ps/' + ref, filename)
gzipFile = gzip.GzipFile(filename)
psFile = open(filename + ".ps","w")
psFile.write(gzipFile.read())
psFile.close()
gzipFile.close()
os.remove(filename)

def downloadSource(ref,type,downloadPath):
downloadPath = os.path.expanduser(downloadPath)
filename = downloadPath + ref.replace('/','-')
urllib.urlretrieve('http://arxiv.org/e-print/' + ref, filename + ".dum")
gzipFile = gzip.GzipFile(filename + ".dum")
sourceFile = open(filename,"w")
sourceFile.write(gzipFile.read())
sourceFile.close()
gzipFile.close()
os.remove(filename + ".dum")

def getTitle(html):
title = html[html.find(">Title:</span>")+15:]
title = title[:title.find("</h1>")]
return title

def getAuthors(html):
authors = html[html.find(">Authors:</span>"):]
authors = authors[authors.find("\">")+2:]
authors = authors[:authors.find("</div>")]
authors = re.sub('<[^>]*>','',authors)
authors = authors.replace("\n","")
return authors

def getAbstract(html):
abstract = html[html.find("Abstract:</span>")+17:]
abstract = abstract[:abstract.find("</blockquote>")-1]
return abstract

def getComments(html):
if "comments" not in html:
return "no comments"
else:
comments = html[html.find("comments\">")+10:]
comments = comments[:comments.find("</td>")]
return comments

def getJref(html):
if "jref" not in html:
return "no journal reference"
else:
jref = html[html.find("jref\">")+6:]
jref = jref[:jref.find("</td>")]
return jref

if __name__ == "__main__":

authorOpt = 0
titleOpt = 0
abstractOpt = 0
commentsOpt = 0
jrefOpt = 0
pdfOpt = 0
psOpt = 0
sourceOpt = 0

try:
options, arguments = getopt.gnu_getopt(sys.argv[1:],
'hatbcjdpsv', ['help'])
except getopt.error:
print 'error: you tried to use an unknown option or the argument for an option that requires it was missing; try \'arxiv.py -h\' for more information'
sys.exit(0)

for o,a in options:
if o in ('-h','--help'):
print __doc__
sys.exit(0)

elif o == '-a':
authorOpt = 1

elif o == '-t':
titleOpt = 1

elif o == '-b':
abstractOpt = 1

elif o == '-c':
commentsOpt = 1

elif o == '-j':
jrefOpt = 1

elif o == '-d':
pdfOpt = 1

elif o == '-p':
psOpt = 1

elif o == '-s':
sourceOpt = 1

if len(options) == 0:
authorOpt = 1
titleOpt = 1
abstractOpt = 1
commentsOpt = 1
jrefOpt = 1

if len(arguments) != 1:
print 'you didn\'t specify an arXiv reference; try \'arxiv.py -h\' for more information'
sys.exit(0)
else:
ref=arguments[0]

type, ref = findRefType(ref)

if type=="not arXiv":
print "type not of arXiv form"
sys.exit(0)

if authorOpt+titleOpt+abstractOpt+commentsOpt+jrefOpt > 0:
htmlObject = urllib.urlopen('http://arxiv.org/abs/' + ref)
html = htmlObject.read()

if titleOpt:
title = getTitle(html)
print title

if authorOpt:
authors = getAuthors(html)
print authors

if abstractOpt:
abstract = getAbstract(html)
print abstract

if commentsOpt:
comments = getComments(html)
print comments

if jrefOpt:
jref = getJref(html)
print jref

if pdfOpt:
downloadPDF(ref,type,"")

if psOpt:
downloadPS(ref,type,"")

if sourceOpt:
downloadSource(ref,type,"")

</pre>

Spires.py

2010-02-05T21:44:12Z

Newacct:

Copy the following text into a file called spires.py with your favourite text editor
<pre>
#! /usr/bin/python

## SPIRES script version 0.3

## Copyright 2007 Tom Brown

## This program is free software; you can redistribute it and/or
## modify it under the terms of the GNU General Public License as
## published by the Free Software Foundation; either version 3 of the
## License, or (at your option) any later version.

## This program is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.

## You should have received a copy of the GNU General Public License
## along with this program. If not, see <http://www.gnu.org/licenses/>.

## See http://www.stringwiki.org/wiki/SPIRES_script for more usage
## instructions

'''SPIRES script
Usage:
python spires.py reference [ -hbiatcev ] [ --help ] [ --library library.bib ] [ --download download_path/ ]
"reference" must be a standard arXiv reference, e.g. hep-th/9711200, 0705.0303, Maldacena:1997re or a SPIRES journal reference, e.g. CMPHA,43,199
Options:
-h, --help
displays this help message
-b
displays the BiBTeX entry
-i
displays the bibitem entry
-a
displays the author(s)
-t
displays the title
-c
displays the TeX citation key
-e
displays everything
-v
verbose mode

--download download_path/
for arXiv references downloads a pdf of the paper from the arXiv to the directory download_path/
--library library.bib
if it is not already in library.bib, appends the BiBTeX entry to library.bib; use at your own risk
'''

__version__ = "0.2"
__author__ = "Tom Brown"
__copyright__ = "Copyright 2007 Tom Brown, GNU GPL 3"

import sys, os, getopt, re, urllib

def findRefType(ref):
ref = ref.replace('arxiv:','')
if re.search(r'^[a-zA-Z\-]+/\d{7}$',ref):
type = 'old-style eprint'
elif re.search(r'^\d{7}$',ref):
type = 'old-style eprint'
ref = 'hep-th/' + ref
elif re.search('^\d{4}\.\d{4}$',ref):
type = 'new-style eprint'
elif re.search(r'^\D+:\d{4}[a-zA-Z]{2}$',ref):
type = 'texkey'
else:
type = 'journal'

return type, ref

def getBiBTeX(ref,type):
if type == 'old-style eprint':
query = 'eprint=' + ref
elif type == 'new-style eprint':
query = 'eprint=arXiv:' + ref
elif type == 'texkey':
query = 'texkey=' + ref
elif type == 'journal':
query = 'j=' + ref
else:
return "no records were found in SPIRES to match your search, please try again"

BiBTeX = urllib.urlopen('http://www.slac.stanford.edu/spires/find/hep/wwwbriefbibtex?' + query + '&server=sunspi5').read()

if 'No records' in BiBTeX:
return "no records were found in SPIRES to match your search, please try again"

BiBTeX = BiBTeX[BiBTeX.find(''):]
BiBTeX = BiBTeX[BiBTeX.find('@'):]

BiBTeX = BiBTeX[:BiBTeX.rfind('')+1]
BiBTeX = BiBTeX[:BiBTeX.rfind('}')+1]

return BiBTeX

def getBibitem(ref,type):
if type == 'old-style eprint':
query = 'eprint=' + ref
elif type == 'new-style eprint':
query = 'eprint=arXiv:' + ref
elif type == 'texkey':
query = 'texkey=' + ref
elif type == 'journal':
query = 'j=' + ref
else:
return "no records were found in SPIRES to match your search, please try again"

bibitem = urllib.urlopen('http://www.slac.stanford.edu/spires/find/hep/wwwbrieflatex2?' + query + '&server=sunspi5').read()

if 'No records' in bibitem:
return "no records were found in SPIRES to match your search, please try again"

bibitem = bibitem[bibitem.find(''):]
bibitem = bibitem[bibitem.find('%'):]

bibitem = bibitem[:bibitem.rfind('')+1]
bibitem = bibitem[:bibitem.rfind('%')+1]

return bibitem

def extractauthor(BiBTeX):
# remove excess white space and replace with a single space
data = re.sub(r'\s+',r' ',BiBTeX)

author = data[data.find('author'):]
author = author[author.find('\"')+1:]
author = author[:author.find('\"')]

return author

def extracttitle(BiBTeX):
# remove excess white space and replace with a single space
data = re.sub(r'\s+',r' ',BiBTeX)

title = data[data.find('title'):]
title = title[title.find('\"')+2:]
title = title[:title.find('\"')-1]

return title

def extractcite(BiBTeX):
cite = BiBTeX[BiBTeX.find('{')+1:BiBTeX.find(',')]
return cite

def downloadeprint(ref,type,downloadPath):
downloadPath = os.path.expanduser(downloadPath)
if type == 'old-style eprint':
urllib.urlretrieve('http://arxiv.org/pdf/' + ref, downloadPath + ref.replace('/','-') + '.pdf')
elif type == 'new-style eprint':
urllib.urlretrieve('http://arxiv.org/pdf/' + ref, downloadPath + ref + '.pdf')

def updatelibrary(cite,BiBTeX,BiBTeXlibraryFileName):
BiBTeXlibraryFileName = os.path.expanduser(BiBTeXlibraryFileName)
libraryfile = open(BiBTeXlibraryFileName, 'r')
library = libraryfile.read()
libraryfile.close()

if cite in library:
print 'adding BiBTeX entry to ' + BiBTeXlibraryFileName
#find the end of the file (the second argument means count from
#the end of the file
libraryfile = open(BiBTeXlibraryFileName, 'a')
libraryfile.write('\n' + BiBTeX + '\n')
libraryfile.close()
else:
print 'BiBTeX entry already in library'

def listCitations(fileName):
fileName = os.path.expanduser(fileName)
f=open(fileName, 'r')
data = f.read()

if r'\begin{thebibliography}' in data:
data = data[:data.find(r'\begin{thebibliography}')]

citations = []

while r'\cite{' in data:
data = data[data.find(r'\cite{') + 6:]
if '}' in data:
citation = data[:data.find('}')]
data = data[data.find('}')+1:]
citation += ','
while ',' in citation:
if citation[:citation.find(',')] not in citations:
citations.append(citation[:citation.find(',')])
citation = citation[citation.find(',')+1:]
return citations

if __name__ == "__main__":

authorOpt = False
titleOpt = False
bibtexOpt = False
bibitemOpt = False
citeOpt = False
verboseOpt = False
libraryOpt = False
downloadOpt = False

try:
options, arguments = getopt.gnu_getopt(sys.argv[1:],
'hbiatcev', ['help','library=','download='])
except getopt.error:
print 'error: you tried to use an unknown option or the argument for an option that requires it was missing; try \'spires.py -h\' for more information'
sys.exit(0)

for o,a in options:
if o in ('-h','--help'):
print __doc__
sys.exit(0)

elif o == '--library':
if a == '':
print '--library expects an argument'
sys.exit(0)
libraryOpt = 1
BiBTeXlibraryFileName = os.path.expanduser(a)
print 'library file name is ' + BiBTeXlibraryFileName

elif o == '--download':
downloadOpt = True
if a == '':
a = './'
elif a[-1] != '/':
a += '/'
downloadPath = os.path.expanduser(a)
print 'download path is ' + downloadPath

elif o == '-b':
bibtexOpt = True

elif o == '-i':
bibitemOpt = True

elif o == '-a':
authorOpt = True

elif o == '-t':
titleOpt = True

elif o == '-c':
citeOpt = True

elif o == '-e':
bibtexOpt = True
authorOpt = True
titleOpt = True
citeOpt = True

elif o == '-v':
verboseOpt = True

if len(arguments) != 1:
print "you didn't specify a SPIRES reference; try 'spires.py -h' for more information"
sys.exit(0)
else:
ref=arguments[0]

if len(options) == 0:
bibtexOpt = True
authorOpt = True
titleOpt = True
citeOpt = True

type, ref = findRefType(ref)

if verboseOpt:
print 'the reference ' + ref + ' is a(n) ' + type

if bibtexOpt or authorOpt or titleOpt or citeOpt or libraryOpt:
BiBTeX = getBiBTeX(ref,type)
if 'no records' in BiBTeX:
print BiBTeX
sys.exit(0)

if bibtexOpt:
print BiBTeX

if bibitemOpt:
bibitem = getBibitem(ref,type)
print bibitem
if 'no records' in bibitem:
sys.exit(0)

if authorOpt:
author = extractauthor(BiBTeX)
print author

if titleOpt:
title = extracttitle(BiBTeX)
print title

if citeOpt or libraryOpt:
cite = extractcite(BiBTeX)

if citeOpt:
print '\cite{' + cite + '}'

if libraryOpt:
updatelibrary(cite,BiBTeX,BiBTeXlibraryFileName)

if downloadOpt:
downloadeprint(ref,type,downloadPath)
</pre>

Spires.py

2009-12-25T10:42:46Z

Newacct:

Copy the following text into a file called spires.py with your favourite text editor
<pre>
#! /usr/bin/python

## SPIRES script version 0.3

## Copyright 2007 Tom Brown

## This program is free software; you can redistribute it and/or
## modify it under the terms of the GNU General Public License as
## published by the Free Software Foundation; either version 3 of the
## License, or (at your option) any later version.

## This program is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.

## You should have received a copy of the GNU General Public License
## along with this program. If not, see <http://www.gnu.org/licenses/>.

## See http://www.stringwiki.org/wiki/SPIRES_script for more usage
## instructions

'''SPIRES script
Usage:
python spires.py reference [ -hbiatcev ] [ --help ] [ --library library.bib ] [ --download download_path/ ]
"reference" must be a standard arXiv reference, e.g. hep-th/9711200, 0705.0303, Maldacena:1997re or a SPIRES journal reference, e.g. CMPHA,43,199
Options:
-h, --help
displays this help message
-b
displays the BiBTeX entry
-i
displays the bibitem entry
-a
displays the author(s)
-t
displays the title
-c
displays the TeX citation key
-e
displays everything
-v
verbose mode

--download download_path/
for arXiv references downloads a pdf of the paper from the arXiv to the directory download_path/
--library library.bib
if it is not already in library.bib, appends the BiBTeX entry to library.bib; use at your own risk
'''

__version__ = "0.2"
__author__ = "Tom Brown"
__copyright__ = "Copyright 2007 Tom Brown, GNU GPL 3"

import sys, os, getopt, re, urllib

def findRefType(ref):
ref = ref.replace('arxiv:','')
if re.search(r'^[a-zA-Z\-]+/\d{7}$',ref):
type = 'old-style eprint'
elif re.search(r'^\d{7}$',ref):
type = 'old-style eprint'
ref = 'hep-th/' + ref
elif re.search('^\d{4}\.\d{4}$',ref):
type = 'new-style eprint'
elif re.search(r'^\D+:\d{4}[a-zA-Z]{2}$',ref):
type = 'texkey'
else:
type = 'journal'

return type, ref

def getBiBTeX(ref,type):
if type == 'old-style eprint':
query = 'eprint=' + ref
elif type == 'new-style eprint':
query = 'eprint=arXiv:' + ref
elif type == 'texkey':
query = 'texkey=' + ref
elif type == 'journal':
query = 'j=' + ref
else:
return "no records were found in SPIRES to match your search, please try again"

BiBTeX = urllib.urlopen('http://www.slac.stanford.edu/spires/find/hep/wwwbriefbibtex?' + query + '&server=sunspi5').read()

if 'No records' in BiBTeX:
return "no records were found in SPIRES to match your search, please try again"

BiBTeX = BiBTeX[BiBTeX.find(''):]
BiBTeX = BiBTeX[BiBTeX.find('@'):]

BiBTeX = BiBTeX[:BiBTeX.rfind('')+1]
BiBTeX = BiBTeX[:BiBTeX.rfind('}')+1]

return BiBTeX

def getBibitem(ref,type):
if type == 'old-style eprint':
query = 'eprint=' + ref
elif type == 'new-style eprint':
query = 'eprint=arXiv:' + ref
elif type == 'texkey':
query = 'texkey=' + ref
elif type == 'journal':
query = 'j=' + ref
else:
return "no records were found in SPIRES to match your search, please try again"

bibitem = urllib.urlopen('http://www.slac.stanford.edu/spires/find/hep/wwwbrieflatex2?' + query + '&server=sunspi5').read()

if 'No records' in bibitem:
return "no records were found in SPIRES to match your search, please try again"

bibitem = bibitem[bibitem.find(''):]
bibitem = bibitem[bibitem.find('%'):]

bibitem = bibitem[:bibitem.rfind('')+1]
bibitem = bibitem[:bibitem.rfind('%')+1]

return bibitem

def extractauthor(BiBTeX):
# remove excess white space and replace with a single space
data = re.sub(r'\s+',r' ',BiBTeX)

author = data[data.find('author'):]
author = author[author.find('\"')+1:]
author = author[:author.find('\"')]

return author

def extracttitle(BiBTeX):
# remove excess white space and replace with a single space
data = re.sub(r'\s+',r' ',BiBTeX)

title = data[data.find('title'):]
title = title[title.find('\"')+2:]
title = title[:title.find('\"')-1]

return title

def extractcite(BiBTeX):
cite = BiBTeX[BiBTeX.find('{')+1:BiBTeX.find(',')]
return cite

def downloadeprint(ref,type,downloadPath):
downloadPath = os.path.expanduser(downloadPath)
if type == 'old-style eprint':
urllib.urlretrieve('http://arxiv.org/pdf/' + ref, downloadPath + ref.replace('/','-') + '.pdf')
elif type == 'new-style eprint':
urllib.urlretrieve('http://arxiv.org/pdf/' + ref, downloadPath + ref + '.pdf')

def updatelibrary(cite,BiBTeX,BiBTeXlibraryFileName):
BiBTeXlibraryFileName = os.path.expanduser(BiBTeXlibraryFileName)
libraryfile = open(BiBTeXlibraryFileName, 'r')
library = libraryfile.read()
libraryfile.close()

if library.count(cite) == 0:
print 'adding BiBTeX entry to ' + BiBTeXlibraryFileName
#find the end of the file (the second argument means count from
#the end of the file
libraryfile = open(BiBTeXlibraryFileName, 'a')
libraryfile.write('\n' + BiBTeX + '\n')
libraryfile.close()
else:
print 'BiBTeX entry already in library'

def listCitations(fileName):
fileName = os.path.expanduser(fileName)
f=open(fileName, 'r')
data = f.read()

if r'\begin{thebibliography}' in data:
data = data[:data.find(r'\begin{thebibliography}')]

citations = []

while r'\cite{' in data:
data = data[data.find(r'\cite{') + 6:]
if '}' in data:
citation = data[:data.find('}')]
data = data[data.find('}')+1:]
citation += ','
while ',' in citation:
if citation[:citation.find(',')] not in citations:
citations.append(citation[:citation.find(',')])
citation = citation[citation.find(',')+1:]
return citations

if __name__ == "__main__":

authorOpt = False
titleOpt = False
bibtexOpt = False
bibitemOpt = False
citeOpt = False
verboseOpt = False
libraryOpt = False
downloadOpt = False

try:
options, arguments = getopt.gnu_getopt(sys.argv[1:],
'hbiatcev', ['help','library=','download='])
except getopt.error:
print 'error: you tried to use an unknown option or the argument for an option that requires it was missing; try \'spires.py -h\' for more information'
sys.exit(0)

for o,a in options:
if o in ('-h','--help'):
print __doc__
sys.exit(0)

elif o == '--library':
if a == '':
print '--library expects an argument'
sys.exit(0)
libraryOpt = 1
BiBTeXlibraryFileName = os.path.expanduser(a)
print 'library file name is ' + BiBTeXlibraryFileName

elif o == '--download':
downloadOpt = True
if a == '':
a = './'
elif a[-1] != '/':
a += '/'
downloadPath = os.path.expanduser(a)
print 'download path is ' + downloadPath

elif o == '-b':
bibtexOpt = True

elif o == '-i':
bibitemOpt = True

elif o == '-a':
authorOpt = True

elif o == '-t':
titleOpt = True

elif o == '-c':
citeOpt = True

elif o == '-e':
bibtexOpt = True
authorOpt = True
titleOpt = True
citeOpt = True

elif o == '-v':
verboseOpt = True

if len(arguments) != 1:
print "you didn't specify a SPIRES reference; try 'spires.py -h' for more information"
sys.exit(0)
else:
ref=arguments[0]

if len(options) == 0:
bibtexOpt = True
authorOpt = True
titleOpt = True
citeOpt = True

type, ref = findRefType(ref)

if verboseOpt:
print 'the reference ' + ref + ' is a(n) ' + type

if bibtexOpt or authorOpt or titleOpt or citeOpt or libraryOpt:
BiBTeX = getBiBTeX(ref,type)
if 'no records' in BiBTeX:
print BiBTeX
sys.exit(0)

if bibtexOpt:
print BiBTeX

if bibitemOpt:
bibitem = getBibitem(ref,type)
print bibitem
if 'no records' in bibitem:
sys.exit(0)

if authorOpt:
author = extractauthor(BiBTeX)
print author

if titleOpt:
title = extracttitle(BiBTeX)
print title

if citeOpt or libraryOpt:
cite = extractcite(BiBTeX)

if citeOpt:
print '\cite{' + cite + '}'

if libraryOpt:
updatelibrary(cite,BiBTeX,BiBTeXlibraryFileName)

if downloadOpt:
downloadeprint(ref,type,downloadPath)
</pre>