Page MenuHomeHEPForge
Files F8310389

get_files.py
No OneTemporary
Actions

get_files.py
View Options

#!/usr/bin/env python
import sys
import os
import string
import urllib
import datetime
#constants
Str_script = "get_files.py : "
#Data sites
Str_dataset_link = "/dbs_discovery/getData"
Str_dbs_runs = "https://cmsweb.cern.ch/dbs_discovery/getRunsFromRange"
Str_dbs_lfn = "https://cmsweb.cern.ch/dbs_discovery/getLFN_txt"
Str_dbs_search = "https://cmsweb.cern.ch/dbs_discovery/aSearchShowAll"
#parameters
str_run = "0"
str_dataset = "/Cosmics/Commissioning08-v1/RAW"
str_extention = "py"
str_output = ""
#variables
int_allrun = 0
int_run = 0
#Getting parameters
for int_count in range(len(sys.argv)):
#-r <Run> if none, use last for given dataset
if sys.argv[int_count] == "-r" :
if int_count < len(sys.argv)-1 :
str_run = sys.argv[int_count+1]
continue
#-d <Dataset>
if sys.argv[int_count] == "-d" :
if int_count < len(sys.argv)-1 :
str_dataset = sys.argv[int_count+1]
continue
#-D <Dataset> force all runs with dataset
if sys.argv[int_count] == "-D" :
if int_count < len(sys.argv)-1 :
str_dataset = sys.argv[int_count+1]
int_allrun = 1
continue
#-f <output file name> if none <dataset>_Run_<Run>_cff.py
if sys.argv[int_count] == "-f" :
if int_count < len(sys.argv)-1 :
str_output = sys.argv[int_count+1]
continue
#-cff
#-py
#-txt
if sys.argv[int_count] == "-cff":
str_extention = "cff"
if sys.argv[int_count] == "-py":
str_extention = "py"
if sys.argv[int_count] == "-txt":
str_extention = "txt"
try:
int_run = int(str_run)
except:
print "%s The run number %s is not an integer" %(Str_script, str_run)
sys.exit(-1)
user_input = 'find run.number,dataset where dataset=' + str_dataset
if int_run > 0 :
user_input = user_input+" and run=" + str_run
print "%sSearching in dbs for %s, %s" %(Str_script,str_run,str_dataset)
else :
print "%sSearching in dbs for %s" %(Str_script,str_dataset)
str_dbs_params = urllib.urlencode({'case':'on','cff':'0','caseSensitive':'on','grid':'0','fromRow':'0','xml':'0','sortName':'Runs_RunRumber','dbsInst':'cms_dbs_prod_global','html':'1','limit':'-1','sortOrder':'desc','output':'run.number,dataset','tabCol':'','userMode':'user','method':'dbsapi','userInput':user_input})
file_dbsRuns = urllib.urlopen(Str_dbs_search, str_dbs_params)
#getting the last run
int_lastRun = 0
int_totRuns = 0
for str_Runs in file_dbsRuns.readlines():
if str_Runs.find(str_dataset) >= 0 :
run_list = str_Runs.split(', '+ str_dataset)
for run in run_list :
if run.find("<br/>") >= 0 :
run=run.split("<br/>")[1]
try:
int(run)
except:
continue
int_totRuns = int_totRuns + 1
if int(run) > int_lastRun :
int_lastRun = int(run)
if int_totRuns == 0 :
print "%sNo entries found"
sys.exit(-1)
print "%sFound %i entries" %(Str_script, int_totRuns)
if int_run == 0 and int_allrun == 0:
print "%sFound last run: %i" %(Str_script, int_lastRun)
int_run = int_lastRun
file_run = open("_tmp_last_run_", 'w')
file_run.write(str(int_lastRun))
str_run = str(int_run)
if str_output == "" :
str_output = str_dataset
if int_allrun == 1:
str_output = str_output+"_AllRuns"
else:
str_output = str_output+"_Run_"+str(int_run)
if str_extention == "cff":
str_output = str_output+".cff"
elif str_extention == "py":
str_output = str_output+"_cff.py"
elif str_extention == "txt":
str_output = str_output+".txt"
str_output = str_output.replace('/','_')
str_output = str_output.replace('-','_')
str_output = str_output.replace('__','_')
#Getting .cff (.py) file list
if int_allrun == 1 :
str_run = "*"
str_lfn_params = urllib.urlencode({'dbsInst':'cms_dbs_prod_global','blockName':'*','dataset':str_dataset,'userMode':'user','run':str_run,'what':str_extention})
file_lfnRuns = urllib.urlopen(Str_dbs_lfn, str_lfn_params)
f = open(str_output, 'w')
for str_dbsLFN in file_lfnRuns.readlines():
f.write(str_dbsLFN)
sys.exit(0)

File Metadata

Mime Type
text/x-python
Expires
Sat, Dec 21, 6:20 PM (8 h, 19 m)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
4023774
Default Alt Text
get_files.py (4 KB)

Event Timeline