PubmedSpreadsheet Generation Code: Difference between revisions
From GersteinInfo
Jump to navigationJump to search
Created page with 'parse_pmids.py: <code> #!/usr/bin/python import os, sys from GoogleSpreadsheet import GoogleSpreadsheet from datetime import datetime master_spreadsheet_id = "thsIyYg12E…' |
No edit summary |
||
| Line 5: | Line 5: | ||
import os, sys | import os, sys | ||
from GoogleSpreadsheet import GoogleSpreadsheet | from GoogleSpreadsheet import GoogleSpreadsheet | ||
from datetime import datetime | from datetime import datetime<br \> | ||
master_spreadsheet_id = "thsIyYg12E8Px0zGJQsAopg" | master_spreadsheet_id = "thsIyYg12E8Px0zGJQsAopg" | ||
worksheet_id = "od6" | worksheet_id = "od6" | ||
master_spreadsheet = GoogleSpreadsheet(master_spreadsheet_id, worksheet_id) | master_spreadsheet = GoogleSpreadsheet(master_spreadsheet_id, worksheet_id)<br \> | ||
ncbiquery = "/home/mpw6/new_papers/ncbiquery.txt" | ncbiquery = "/home/mpw6/new_papers/ncbiquery.txt" | ||
ncbiFile = open(ncbiquery,'w') | ncbiFile = open(ncbiquery,'w')<br \> | ||
def buildQuery(master_spreadsheet, ncbiFile): | def buildQuery(master_spreadsheet, ncbiFile): | ||
start = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=" | start = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=" | ||
| Line 23: | Line 20: | ||
pmids = pmids[:-1] | pmids = pmids[:-1] | ||
out = start + pmids + end + '\n' | out = start + pmids + end + '\n' | ||
ncbiFile.write(out) | ncbiFile.write(out)<br \> | ||
buildQuery(master_spreadsheet, ncbiFile) | buildQuery(master_spreadsheet, ncbiFile) | ||
</code> | </code> | ||
Revision as of 11:03, 16 September 2011
parse_pmids.py:
#!/usr/bin/python
import os, sys
from GoogleSpreadsheet import GoogleSpreadsheet
from datetime import datetime
master_spreadsheet_id = "thsIyYg12E8Px0zGJQsAopg"
worksheet_id = "od6"
master_spreadsheet = GoogleSpreadsheet(master_spreadsheet_id, worksheet_id)
ncbiquery = "/home/mpw6/new_papers/ncbiquery.txt"
ncbiFile = open(ncbiquery,'w')
def buildQuery(master_spreadsheet, ncbiFile):
start = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id="
pmids =
end = "&rettype=xml&retmode=file"
for row in master_spreadsheet:
if row['pmid']:
pmids += row['pmid'].lstrip('\) + ','
pmids = pmids[:-1]
out = start + pmids + end + '\n'
ncbiFile.write(out)
buildQuery(master_spreadsheet, ncbiFile)
