pull study info from OTI

gen-curl-oti.py

#!/usr/bin/env
import sys

'''
python gen-curl-oti.py template.txt studies.txt
where studies.txt is the list of studies used in synthesis.
  and template is a cURL call with XYZ inplace of the study id (and no other XYZ)
cURL
'''

if False:
  template = open(sys.argv[1], 'rU').read().strip()
else:
  # when I ran this, template contained:
  template = '''curl 'https://api.opentreeoflife.org/oti/v1/singlePropertySearchForStudies' -H 'Origin: https://tree.opentreeoflife.org' -H 'Accept-Encoding: gzip, deflate' -H 'Accept-Language: en-US,en;q=0.8' -H 'User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.93 Safari/537.36' -H 'Content-Type: application/x-www-form-urlencoded; charset=UTF-8' -H 'Accept: */*' -H 'Referer: https://tree.opentreeoflife.org/opentree/argus/ottol@158484/Pan-paniscus' -H 'Connection: keep-alive' --data 'property=ot%3AstudyId&value=XYZ&verbose=true' --compressed'''

ts = template.split('XYZ')
assert len(ts) == 2
study_list = [i.strip() for i in open(sys.argv[2], 'rU').readlines() if i.strip()]
for s in study_list:
  ns = s.join(ts)
  print ns, '>', s + '.out'

redirect stdout to run.sh and then bash run.sh in a clean directory.