def return_tree(s, target, rootfilename, **kwargs):
load_flag = kwargs.get("Load")
if load_flag != False and FileSys.file_check_json(s, rootfilename):
if load_flag == None:
load_flag = MyUtil.get_yn("File already exists. [Load from disk = Y, re-create = N] (Y/N)?")
tr = FileSys.file_read_json(rootfilename)
return tr
tr = get_tree(s, target)
# print_tree(s, tr)
FileSys.file_write_json(tr, rootfilename, path=CF.dccfilepath)
return tr
def return_tree(s, target, rootfilename, **kwargs):
load_flag = kwargs.get('Load')
if FileSys.file_check_json(s, rootfilename) == True:
if load_flag == None:
print('File [',rootfilename,'] already exists - use existing file? ', sep = '', end = '')
load_flag = MyUtil.get_yn('[Load from disk = Y, re-create = N] (Y/N)? ')
if load_flag == True:
tr = FileSys.file_read_json(rootfilename)
FileSys.file_write_json(tr, rootfilename, path = CF.dccfilepath)
return(tr)
tr = get_tree(s,target, **kwargs)
FileSys.file_write_json(tr, rootfilename, path = CF.dccfilepath)
# print_tree(s, tr)
return(tr)
def return_tree(s, target, rootfilename, **kwargs):
load_flag = kwargs.get('Load')
if FileSys.file_check_json(s, rootfilename) == True:
if load_flag == None:
print('File [', rootfilename, '] already exists ', sep='', end='')
load_flag = MyUtil.get_yn(
'[Load from disk = Y, re-create = N] (Y/N)?')
if load_flag == True:
tr = FileSys.file_read_json(rootfilename)
FileSys.file_write_json(tr, rootfilename, path=CF.dccfilepath)
return (tr)
tr = get_tree(s, target, **kwargs)
FileSys.file_write_json(tr, rootfilename, path=CF.dccfilepath)
# print_tree(s, tr)
return (tr)
def prop_get(s, handle, **kwargs):
# kwargs options:
# Depth - Level to get Collection children information ('0', '1' or 'infinity')
# '0' returns information on Collection itself
# '1' and 'infinity' return information on Collection content
# InfoSet = Children - Collection Children
# InfoSet = CollData - Information about Collection
# InfoSet = CollCont - Information about Collection Content (See Depth)
# InfoSet = DocBasic - Document basic information
# InfoSet = DocDate - Document last modified date
# InfoSet = Group - Group information
# InfoSet = Parents - Locations of documents or collections
# InfoSet = Perms - Document Permissions
# InfoSet = User - User information
# InfoSet = VerAll - All Version information
# RetDom - Return BeautifulSoup object rather than file data structure
# WriteProp = (True|False) - Write .html to disk?
# Print = (True|False) - Call print function on InfoSet?
url = DCC_URL + "/dsweb/PROPFIND/" + handle
headers = {
"DocuShare-Version": "5.0",
"Content-Type": "text/xml",
"Accept": "text/xml"
}
infoDic = {
'Children': '<children/>',
'CollCont': '<title/><summary/><entityowner/><getlastmodified/>',
'CollData':
'<title/><summary/><keywords/><entityowner/><getlastmodified/>',
'DocBasic':
'<author/><handle/><document/><getlastmodified/><size/><summary/><entityowner/><keywords/>',
'DocDate': '<getlastmodified/>',
'Group': '<entityowner/><handle/><parents/><children/>',
'Parents': '<parents/>',
'Perms': '<private/><acl/>',
'Summary': '<summary/>',
'Title': '<handle/>',
'User': '******',
'VerAll':
'<revision_comments/><title/><version_number/><parents/><handle/><entityowner/><getlastmodified/>',
'Versions': '<versions/><document_tree/>'
}
infoSet = kwargs.get('InfoSet', 'DocBasic')
if debug: print('infoSet:', infoSet)
writeRes = kwargs.get('WriteProp', False)
retDom = kwargs.get('RetDom', False)
depth = kwargs.get('Depth', '0')
headers['Depth'] = depth
printFlag = kwargs.get('Print', False)
if infoSet == 'CollCont':
fRoot = handle + '_' + infoSet + depth
else:
fRoot = handle + '_' + infoSet
if debug: print('fRoot:', fRoot)
if infoSet == 'DocDate':
isCached = False
else:
[isCached, fd] = FileSys.check_cache_fd_json(s, handle, infoSet, fRoot)
if debug: print('isCached:', isCached)
if not isCached:
if debug: print('Calling DCC API from prop_get: ', infoSet, handle)
if infoSet in infoDic:
xml = """<?xml version="1.0" ?><propfind><prop>""" + infoDic[
infoSet] + """</prop></propfind>"""
r = s.post(url, data=xml, headers=headers)
else:
print('Calling without XML')
r = s.post(url, headers=headers)
if writeRes:
FileSys.file_write_props(r, fRoot)
dom = BeautifulSoup(r.text)
if retDom:
return (dom)
if infoSet in infoDic:
fd = prop_scrape(dom, infoSet)
FileSys.file_write_json(fd, fRoot)
if printFlag:
prop_print(infoSet, fd)
return (fd)
def prop_get(s, handle, **kwargs):
# kwargs options:
# Depth - Level to get Collection children information ('0', '1' or 'infinity')
# '0' returns information on Collection itself
# '1' and 'infinity' return information on Collection content
# InfoSet = Children - Collection Children
# InfoSet = CollData - Information about Collection
# InfoSet = CollCont - Information about Collection Content (See Depth)
# InfoSet = DocBasic - Document basic information
# InfoSet = DocDate - Document last modified date
# InfoSet = Group - Group information
# InfoSet = Parents - Locations of documents or collections
# InfoSet = Perms - Document Permissions
# InfoSet = User - User information
# InfoSet = VerAll - All Version information
# RetDom - Return BeautifulSoup object rather than file data structure
# WriteProp = (True|False) - Write .html to disk?
# Print = (True|False) - Call print function on InfoSet?
url = DCC_URL + "/dsweb/PROPFIND/" + handle
headers = {"DocuShare-Version":"5.0", "Content-Type":"text/xml", "Accept":"text/xml"}
infoDic = { 'Children' : '<children/>',
'CollCont' : '<title/><summary/><entityowner/><getlastmodified/>',
'CollData' : '<title/><summary/><keywords/><entityowner/><getlastmodified/>',
'DocBasic':'<author/><handle/><document/><getlastmodified/><size/><summary/><entityowner/><keywords/>',
'DocDate': '<getlastmodified/>',
'Group': '<entityowner/><handle/><parents/><children/>',
'Parents': '<parents/>',
'Perms': '<private/><acl/>',
'Summary' : '<summary/>',
'Title': '<handle/>',
'User': '******',
'VerAll' : '<revision_comments/><title/><version_number/><parents/><handle/><entityowner/><getlastmodified/>',
'Versions' : '<versions/><document_tree/>'}
infoSet = kwargs.get('InfoSet','DocBasic')
if debug: print('infoSet:',infoSet)
writeRes = kwargs.get('WriteProp', False)
retDom = kwargs.get('RetDom',False)
depth = kwargs.get('Depth','0')
headers['Depth'] = depth
printFlag = kwargs.get('Print', False)
if infoSet == 'CollCont':
fRoot = handle + '_' + infoSet + depth
else:
fRoot = handle + '_' + infoSet
if debug: print('fRoot:', fRoot)
if infoSet == 'DocDate':
isCached = False
else:
[isCached, fd] = FileSys.check_cache_fd_json(s, handle, infoSet, fRoot)
if debug: print('isCached:', isCached)
if not isCached:
if debug: print('Calling DCC API from prop_get: ',infoSet, handle)
if infoSet in infoDic:
xml = """<?xml version="1.0" ?><propfind><prop>""" + infoDic[infoSet] + """</prop></propfind>"""
r = s.post(url,data=xml,headers=headers)
else:
print('Calling without XML')
r = s.post(url,headers=headers)
if writeRes:
FileSys.file_write_props(r, fRoot)
dom = BeautifulSoup(r.text, "html.parser")
if retDom:
return(dom)
if infoSet in infoDic:
fd = prop_scrape(dom, infoSet)
FileSys.file_write_json(fd, fRoot)
if printFlag:
prop_print(infoSet,fd)
return(fd)
