Browse Source

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

onlinkgen
alpcentaur 1 year ago
parent
commit
317ef99720
2 changed files with 53 additions and 26 deletions
  1. BIN
      spiders/__pycache__/fdb_spider.cpython-39.pyc
  2. +53
    -26
      spiders/fdb_spider.py

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


+ 53
- 26
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]
try:
name = tree.xpath(
fdb_conf_entry_list_parent
+ "["
+ str(n+1)
+ "]"
+ fdb_conf_entry_list_child_name
)[0]
info = tree.xpath(
fdb_conf_entry_list_parent
+ fdb_conf_entry_list_child_info
)[n]
except Exception as e:
print("name could not be parsed", e)
name = 'NONE'
try:
info = tree.xpath(
fdb_conf_entry_list_parent
+ "["
+ str(n+1)
+ "]"
+ fdb_conf_entry_list_child_info
)[0]
period = tree.xpath(
fdb_conf_entry_list_parent
+ fdb_conf_entry_list_child_period
)[n]
print('oi ', name)
print('blablidubbiduub')
link = tree.xpath(
fdb_conf_entry_list_parent
# + "["
# + str(n)
# + "]"
+ fdb_conf_entry_list_child_link
)[n]
print('oi' + name)
except Exception as e:
print("info could not be parsed", e, info)
info = 'NONE'
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:
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

Loading…
Cancel
Save