alpcentaur/fdb-spider
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

changed code in entrylist data2dictionary to handle empty or missing xml elements

Browse source
This commit is contained in:
alpcentaur 2023-11-14 10:22:26 +00:00
parent ff23c22e3c
commit 317ef99720
2 changed files with 54 additions and 27 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

BIN
spiders/__pycache__/fdb_spider.cpython-39.pyc
View file

Binary file not shown.

75
spiders/fdb_spider.py
View file

@ -218,35 +218,62 @@ class fdb_spider(object):
print('blabliblub') print('blabliblub')
print('len', len(tree.xpath(fdb_conf_entry_list_parent))) print('len', len(tree.xpath(fdb_conf_entry_list_parent)))
for n in range(len(tree.xpath(fdb_conf_entry_list_parent))): for n in range(len(tree.xpath(fdb_conf_entry_list_parent))):
print('oi inside the loop')
name = tree.xpath(
fdb_conf_entry_list_parent
+ fdb_conf_entry_list_child_name
)[n]
info = tree.xpath( try:
fdb_conf_entry_list_parent name = tree.xpath(
+ fdb_conf_entry_list_child_info fdb_conf_entry_list_parent
)[n] + "["
+ str(n+1)
+ "]"
+ fdb_conf_entry_list_child_name
)[0]
period = tree.xpath( except Exception as e:
fdb_conf_entry_list_parent print("name could not be parsed", e)
+ fdb_conf_entry_list_child_period name = 'NONE'
)[n]
print('oi ', name) try:
print('blablidubbiduub') info = tree.xpath(
link = tree.xpath( fdb_conf_entry_list_parent
fdb_conf_entry_list_parent + "["
# + "[" + str(n+1)
# + str(n) + "]"
# + "]" + fdb_conf_entry_list_child_info
+ fdb_conf_entry_list_child_link )[0]
)[n]
print('oi' + name) except Exception as e:
print("info could not be parsed", e, info)
info = 'NONE'
if len(name) > 0: try:
period = tree.xpath(
fdb_conf_entry_list_parent
+ "["
+ str(n+1)
+ "]"
+ fdb_conf_entry_list_child_period
)[0]
print('period', period)
except Exception as e:
print("period could not be parsed", e, period)
period = 'NONE'
try:
link = tree.xpath(
fdb_conf_entry_list_parent
+ "["
+ str(n+1)
+ "]"
+ fdb_conf_entry_list_child_link
)[0]
print('link', link)
except Exception as e:
print("link could not be parsed", e, link)
link = 'NONE'
if len(name) > 0 and name != 'NONE':
dictionary_entry_list[n] = {} dictionary_entry_list[n] = {}
dictionary_entry_list[n]["name"] = name dictionary_entry_list[n]["name"] = name
dictionary_entry_list[n]["info"] = info dictionary_entry_list[n]["info"] = info