Build Papers Page Code

From GersteinInfo

Revision as of 11:38, 16 September 2011 by Public (Talk | contribs)
Jump to: navigation, search

update.py

Basic Setup 

#!/usr/bin/python
import os, sys, re
from GoogleSpreadsheet import GoogleSpreadsheet
from datetime import datetime

pubmed_spreadsheet_id = "*******************"
master_spreadsheet_id = "********************"
subject_spreadsheet_id = "*************************"
worksheet_id = "od6"
pubmed_spreadsheet = GoogleSpreadsheet(pubmed_spreadsheet_id, worksheet_id)
master_spreadsheet = GoogleSpreadsheet(master_spreadsheet_id, worksheet_id)
subject_spreadsheet = GoogleSpreadsheet(subject_spreadsheet_id, worksheet_id)
timestamp = str(datetime.now().ctime())

summaryPath = "************"
summaryIndex = "*********************"
summaryFile = open(summaryIndex,'w')
simpleIndex = "*************"
simpleFile = open(simpleIndex,'w')
subjectPath = "********************"
subjectIndex = subjectPath + "index.html"
subjectFile = open(subjectIndex,'w')
subjectSummaryIndex = "******************"
subjectSummaryFile = open(subjectSummaryIndex,'w')

header = '''
***********
'''

def printPapers(master_spreadsheet,summaryFile, header): out = "<HTML>\n" out += "<HEAD>\n" out += "<TITLE>Gerstein Lab Publications</TITLE>\n" out += header out += "\n"

out += "
\n"

out += "Main Scientific Publications\n" out += "\n"

out += "

Total papers: " + str(len(master_spreadsheet)) + "

\n" out += "

(Last updated " + timestamp + ")</CENTER>\n" years = {} currentYear = 0 for row in master_spreadsheet: rowYear = row['year'] if years.has_key(rowYear): years[rowYear] += 1 else: years[rowYear] = 1 for row in master_spreadsheet: pubmed = pubmed_spreadsheet if currentYear != row['year']: currentYear = row['year'] out += "

-- " + currentYear + " (" + str(years[currentYear]) + ") --

"

summaryFile.write(out) simpleFile.write(out) simpleFile2.write(out) out = "" printPaperEntry(row, summaryFile, pubmed) printSimpleEntry(row, simpleFile, pubmed) printSimpleEntry(row,simpleFile2,pubmed) printEntrySummary(row, header, pubmed) printEntryExtended(row) out = "</BODY></HTML>" summaryFile.write(out) simpleFile.write(out)

def printEntrySummary(row,header,pubmed): #if row['pmid']: #print 'pES first: ' + row['pmid'] #else: #print 'pES first: no pmid' pubmed.count = 0 for pubmed_row in pubmed: #print 'pES pubmed: ' + pubmed_row['pmid'] if row['pmid'] == pubmed_row['pmid']: row['title'] = pubmed_row['title'] row['citation'] = pubmed_row['citation'] row['authors'] = pubmed_row['authors'] row['year'] = pubmed_row['year'] break # create summary directory entrySummary = summaryPath + row['labid'].lstrip('\) if not os.path.exists(entrySummary): os.makedirs(entrySummary) entrySummaryIndex = entrySummary + "/index.html" entrySummaryFile = open(entrySummaryIndex,'w')

out = "<HTML>\n" out += "<HEAD>\n" out += "<TITLE>" + row['title'].lstrip('\) + "</TITLE>" out += header out += "\n"

out += "
\n" out += "" + row['labid'] + "<p />" out += "\n" # print title and citation out += "
<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index.html\">" + row['title'].lstrip('\) + "</A>
\n"

if row.has_key('authors'):

out += "
" +row['authors'].lstrip('\)+ " " +row['citation'].lstrip('\) + "
\n"

else:

out += "
" + " " + row['citation'].lstrip('\) + "
\n"

# print links

out += "
"

if not row['website']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"" + row['website'].lstrip('\) + "\"><IMG SRC=\"/papers/website.jpg\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\"></A>" if not row['preprint']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"" + row['preprint'].lstrip('\) + "\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/preprint.jpg\"></A>" if not row['pmid']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"http://www.ncbi.nlm.nih.gov:80/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=" + row['pmid'].lstrip('\) + "&dopt=Abstract\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/medline.jpg\"></A>" #if not labid: # out += "<A HREF=\"#\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>" #else: out += "<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index-all.html\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>"

out += "
\n<P />\n" out += "

<a href=index-all.html>View all citation information</a>
<a href='/'>Return to papers index</a>
 
</BODY></HTML>"

entrySummaryFile.write(out)

def printEntryExtended(row): title = citation = authors = journal = pages = volume = year = pmcid =

for pubmed_row in pubmed_spreadsheet: if row['pmid'] == pubmed_row['pmid']: title = pubmed_row['title'] citation = pubmed_row['citation'] authors = pubmed_row['authors'] year = pubmed_row['year'] journal = pubmed_row['journal'] pages = pubmed_row['pages'] volume = pubmed_row['volume'] pmcid = pubmed_row['pmcid']

# create summary directory entryExtended = summaryPath + row['labid'].lstrip('\) if not os.path.exists(entryExtended): os.makedirs(entryExtended) entryExtendedIndex = entryExtended + "/index-all.html" entryExtendedFile = open(entryExtendedIndex,'w')

out = "<HTML>\n" out += "<HEAD>\n" if not title: out += "<TITLE>" + row['title'].lstrip('\) + "</TITLE>" else: out += "<TITLE>" + title.lstrip('\) + "</TITLE>" out += header out += "\n"

out += "
\n" if not row['labid']: out += "" + row['pmid'].lstrip('\) + "<p />" else: out += "" + row['labid'] + "<p />" out += "\n" # print title and citation if not title: out += "
<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index.html\">" + row['title'].lstrip('\) + "</A>
\n"

else:

out += "
<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index.html\">" + title.lstrip('\) + "</A>
\n"

if not citation: if not row.has_key('authors'):

out += "
" + " " + row['citation'].lstrip('\) + "
\n" # out += "
" + " " + row['citation'].lstrip('\) + "
\n"

else:

out += "
" + row['authors'].lstrip('\) + " " +row['citation'].lstrip('\) + "
\n"

else:

out += "
" + authors.lstrip('\) + ' ' + citation.lstrip('\) + "
\n"

# print links

out += "
"

if not row['website']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"" + row['website'].lstrip('\) + "\"><IMG SRC=\"/papers/website.jpg\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\"></A>" if not row['preprint']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"" + row['preprint'].lstrip('\) + "\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/preprint.jpg\"></A>" if not row['pmid']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"http://www.ncbi.nlm.nih.gov:80/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=" + row['pmid'].lstrip('\) + "&dopt=Abstract\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/medline.jpg\"></A>" #if not labid: # out += "<A HREF=\"#\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>" #else: out += "<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index-all.html\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>"

out += "
\n<P />\n" out += '<A HREF="index.html">Switch to compact view</A>
\n\n'

if not authors:

out += '\n'

else:

out += '\n' if not journal: out += '\n'

else:

out += '' if not row['pmid']: out += "\n"

else:

out += '\n' if not pages: out += "\n"

else:

out += "\n"

if not volume:

out += "\n"

else:

out += "\n"

if not year:

out += "\n"

else:

out += "\n" out += "\n"

if not row['labid']:

out += "\n"

else:

out += "\n"

if not title:

out += "\n"

else:

out += "\n"

if not row['subject']:

out += "\n"

else: subjects = row['subject'].split(',') num_subjects = len(subjects)

out += '\n' if not row['website']: out += "\n"

else:

out += '\n' out += "
Authors 
Authors'

link = '<A HREF="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=PureSearch&db=PubMed&details_term=%s">%s</A>' authorlinks = [link % (a.lstrip('\).strip().replace(' ','%20'),a.lstrip('\).strip()) for a in authors.split(',')] # print authorlinks out += ', '.join(authorlinks)

out += '
Journal 
Journal'

out += '<A HREF="http://locatorplus.gov/cgi-bin/Pwebrecon.cgi?DB=local&v2=1&ti=1,1&Search_Arg=9808944&Search_Code=0359&CNT=20&SID=1">'

out += journal + '</A>
PMID 
PMID'

out += '<A HREF="http://www.ncbi.nlm.nih.gov:80/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=' + row['pmid'].lstrip('\) + '&dopt=Abstract">'

out += row['pmid'].lstrip('\) + '</A>
Pages 
Pages" + pages.lstrip('\) + "
Volume 
Volume" + volume.lstrip('\) + "
Year 
Year" + year.lstrip('\) + "
labcite" + citation.lstrip('\) + "
labid 
labid" + row['labid'].lstrip('\) + "
labtitle 
labtitle" + title.lstrip('\) + "
subject 
subject'

subject_count = 0 for subject in subjects: out += '<A HREF="/subject/' + subject.lstrip('\' ') + '">' + subject.lstrip('\' ') + '</A>' subject_count += 1 if subject_count < num_subjects: out += ', '

out += '
website 
website<A HREF="'+row['website'].lstrip('\)+'">'+row['website'].lstrip('\)+'</A>

Unused tags: e-print footnote grant ignore preprint sortval target website2
<a href='/'>Return to papers index</a>
 
</BODY></HTML>"

entryExtendedFile.write(out)

def printPaperEntry(row, summaryFile, pubmed): title = citation = authors = year = for pubmed_row in pubmed: if row['pmid'] == pubmed_row['pmid']: title = pubmed_row['title'] citation = pubmed_row['citation'] authors = pubmed_row['authors'] year = pubmed_row['year'] break # print title and citation if not title:

out = "
<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index.html\">" + row['title'] + "</A>
\n"

else:

out = "
<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index.html\">" + title.lstrip('\) + "</A>
\n"

if not citation: if not row.has_key('authors'):

out += "
" + row['citation'].lstrip('\) + "
\n"

else:

out += "
" + row['authors'].lstrip('\) + " " + row['citation'].lstrip('\) + "
\n"

else:

out += "
" + authors.lstrip('\) + " " + citation.lstrip('\) + "
\n"

# print links

out += "
"

if not row['website']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"" + row['website'].lstrip('\) + "\"><IMG SRC=\"/papers/website.jpg\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\"></A>" if not row['preprint']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"" + row['preprint'].lstrip('\) + "\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/preprint.jpg\"></A>" if not row['pmid']: out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">" else: out += "<A HREF=\"http://www.ncbi.nlm.nih.gov:80/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=" + row['pmid'].lstrip('\) + "&dopt=Abstract\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/medline.jpg\"></A>" #if not labid: # out += "<A HREF=\"#\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>" #else: out += "<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index-all.html\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>"

out += "
\n<P />\n"

summaryFile.write(out)

def printSimpleEntry(row, simpleFile, pubmed): pmid = title = citation = authors = year = #if row['pmid']: #print 'pSE first: ' + row['pmid'] #else: #print 'pSE first: no pmid' pubmed.count = 0 for pubmed_row in pubmed: #print 'pSE pubmed: ' + pubmed_row['pmid'] if row['pmid'] == pubmed_row['pmid']: pmid = pubmed_row['pmid'] title = pubmed_row['title'] citation = pubmed_row['citation'] authors = pubmed_row['authors'] year = pubmed_row['year'] pmcid = pubmed_row['pmcid'] break #else: #print 'no match' if row['pmid']: out = '

' + authors.lstrip('\) + ' (' + year.lstrip('\) + '). "' + title.lstrip('\) +'" ' p = re.compile("\(\d+\)\.") p2 = re.compile(":") citation = p.sub("",citation) citation = p2.sub(": ",citation) out += citation.lstrip('\) + ' [PMID: ' + pmid + '].
\n' else: #if not row['authors']: out = '
' +'"' + row['title'].lstrip('\) + '." ' #out = '
' + ' (' + row['year'].lstrip('\) + '). "' + row['title'].lstrip('\) +'" ' #else: #out = '
' + row['authors'].lstrip('\) + ' (' + row['year'].lstrip('\) + '). "' + row['title'].lstrip('\) +'" ' out += row['citation'].lstrip('\) + '
\n' simpleFile.write(out)

def printSubject(master_spreadsheet,header): allsubjects = [] subjectpapers = [] for i,row in enumerate(master_spreadsheet): if row.has_key('subject') and row['subject']: #and row['pmid'].isdigit(): subjects = row['subject'].split(',') for subject in subjects: subject = subject.strip( ) if subject not in allsubjects: allsubjects.append(subject) subjectpapers.append([i]) else: index = allsubjects.index(subject) subjectpapers[index].append(i)

for row in subject_spreadsheet: subject = row['labid'].strip( ) if subject not in allsubjects: path = subjectPath + subject if not os.path.exists(path): os.makedirs(path) subjectFile = open(path + '/index.html', 'w') out = <HTML> <HEAD> <TITLE>%s</TITLE> %subject.capitalize()

out +=header include = if row['html']: include =row['html'].lstrip('\) if include: out += include subjectFile.write(out)

subjectFile.write('</FONT>
<A HREF = "/">Return to front page</A>\n</BODY></HTML>')

subjectFile.close()

for i,subject in enumerate(allsubjects): printSubjectFile(subject,subjectpapers[i])

def printSubjectFile(subject,papers): path = subjectPath + subject if not os.path.exists(path): os.makedirs(path) subjectFile = open(path + '/index.html','w')

  1. subjectInclude = path + '/include.html'

out = <HTML> <HEAD> <TITLE>%s</TITLE>  % subject.capitalize() out += header

#include include file if exists

  1. if os.path.exists(subjectInclude):
  2. includeFile = open(subjectInclude,'r')
  3. for line in includeFile:
  4. subjectFile.write(line + '\n')
  5. includeFile.close()
  6. subjectFile.write('\n\n')

include = for row in subject_spreadsheet: if row['labid'] == subject: if row['html']: include = row['html'].lstrip('\) if include: out += include subjectFile.write(out)

for r in papers: printSubjectEntry(subjectFile,r)

subjectFile.write(' </FONT>
<A HREF= "/">Return to front page</A>\n</BODY></HTML>')

subjectFile.close()

def printSubjectEntry(subjectFile,r): row = master_spreadsheet.rows[r] found = False for sr in pubmed_spreadsheet: if row['pmid'] == sr['pmid']: #row['labid'] = sr['labid'] row['title'] = sr['title'] row['authors'] = sr['authors'] row['year'] = sr['year'] row['citation'] = sr['citation'] #row['website'] = sr['website'] #row['preprint'] = sr['preprint'] found = True # break if found: 

       	# print title and citation

if not row['labid']:

out = "
" + row['title'].lstrip('\) + "</A>
\n"

else:

out = "
<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index.html\">" + row['title'].lstrip('\) + "</A>
\n" out += "
" + row['authors'].lstrip('\) + " " + row['citation'].lstrip('\) + "
\n" 
       	# print links
out += "
" 
       	if not row['website']:
               	out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">"
       	else:
               	out += "<A HREF=\"" + row['website'].lstrip('\)  + "\"><IMG SRC=\"/papers/website.jpg\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\"></A>"
       	if not row['preprint']:
               	out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">"
       	else:
               	out += "<A HREF=\"" + row['preprint'].lstrip('\) + "\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/preprint.jpg\"></A>"
       	if not row['pmid']:
               	out += "<IMG SRC=\"/papers/null.gif\" HEIGHT=\"23\" WIDTH=\"56\" BORDER=\"0\">"
       	else:
               	out += "<A HREF=\"http://www.ncbi.nlm.nih.gov:80/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=" + row['pmid'].lstrip('\) + "&dopt=Abstract\"><IMG BORDER=\"0\" HEIGHT=\"23\" WIDTH=\"56\" SRC=\"/papers/medline.jpg\"></A>"
       	if not row['labid']:
               	out += "<A HREF=\"#\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>"
       	else:
               	out += "<A HREF=\"/papers/" + row['labid'].lstrip('\) + "/index-all.html\">" + "<IMG BORDER=\"0\" WIDTH=\"23\" HEIGHT=\"23\" SRC=\"/papers/more.gif\"></A>"
out += "
\n<P />\n"

subjectFile.write(out)

def printSubjectSummary(subject_spreadsheet, subjectSummaryFile, header): styleSubject =
<STYLE type="text/css"> .unsel{background-color:#ffffff; background-position:top; background-repeat:repeat-x; color:#FFFFFF; font-weight:normal;} .sel {background-color:#3b5998; color:#FFFFFF; font-weight:normal;} .content{background-color:#ffffff; height:25px; padding-left:20px; padding-right:20px; padding-top:20px;color:#ffffff;} 

       a{text-decoration:none;color:#ffffff;}

.unsel a:link {color:#888888;text-decoration:none;} .sel a:visited {color:#ffffff;text-decoration:none;} .sel a:active {color:#ffffff;text-decoration:none;} .sel a:hover {color:#ffffff;text-decoration:underline;} </STYLE>

category = SubjectNumber = 0 outPart = out = "<HTML>\n" out += "<HEAD>\n" out += "<TITLE>Gerstein Lab Publications</TITLE>\n" out += header out += "\n" out += styleSubject out += '<BODY onload="javascript:showdh(3);">\n'

out += '\n\n\n'

for row in subject_spreadsheet: if not category == row['category'].lstrip('\): if not category == :

outPart += "</TD>\n" SubjectNumber +=1 tableid = str(SubjectNumber) category = row['category'].lstrip('\) out +='<TD width="86" class="unsel" id="dh'+tableid+'">
<A href="javascript:showdh('+tableid+');" _fcksavedurl="javascript:showdh('+tableid+');">'+ row['category'].lstrip('\) + '</A>
</TD>\n'

out += ' <TD width="6"></TD>\n' outPart +='<TR id="menu'+ tableid+'" style="display:none">\n' outPart +='<TD class="content" style="line-height:25px">\n' outPart += " <A HREF='/subject/" + row['labid'].lstrip('\)+"/index.html' STYLE='text-decoration:none; color:black'>" title = str(row['title']) outPart += "[ "+row['labid'].lstrip('\)+" ] "+title.lstrip('\)+"</A>
\n" outPart += "</TD></TR>\n"

out += '</TR></TABLE>\n
\n' out += outPart out += <script language="javascript"> function showdh(n){ for(var i=1;i<= + tableid+;i++){ eval("dh" + i).className="unsel" eval("menu"+i).style.display="none"; } eval("dh"+n).className="sel" eval("menu"+n).style.display=""; } </script> out += "</BODY></HTML>" subjectSummaryFile.write(out) printSubjectSummary(subject_spreadsheet, subjectSummaryFile, header) printSubject(master_spreadsheet,header) printPapers(master_spreadsheet, summaryFile, header) </pre>
Retrieved from "http://info.gersteinlab.org/Build_Papers_Page_Code"
Personal tools