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

added some exceptions for bad encoding and get errors

Browse source
This commit is contained in:
alpcentaur 2023-11-14 14:38:45 +00:00
parent 317ef99720
commit 42841ee650
3 changed files with 32 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
main.py
View file

@ -13,9 +13,9 @@ spider = fdb_spider(config)
#spider.find_config_parameter(list_of_fdbs)
spider.parse_entry_list_data2dictionary(list_of_fdbs)
#spider.parse_entry_list_data2dictionary(list_of_fdbs)
# spider.download_entry_data_htmls(list_of_fdbs)
spider.download_entry_data_htmls(list_of_fdbs)
# spider.parse_entry_data2dictionary(list_of_fdbs)

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

Binary file not shown.

34
spiders/fdb_spider.py
View file

@ -281,8 +281,10 @@ class fdb_spider(object):
if fdb_domain in link:
dictionary_entry_list[n]["link"] = link
if fdb_domain not in link and ('http:' in link or 'www.' in link or 'https:' in link):
dictionary_entry_list[n]["link"] = link
if fdb_domain not in link:
else:
if link[-1] == '/':
dictionary_entry_list[n]["link"] = fdb_domain + link
else:
@ -323,9 +325,33 @@ class fdb_spider(object):
entry_link = dictionary_entry_list[entry_id]["link"]
# download the html page of the entry
response = urllib.request.urlopen(entry_link)
web_content = response.read().decode("UTF-8")
try:
url = entry_link
req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0', 'Cookie':'myCookie=lovely'})
response = urllib.request.urlopen(req)
except Exception as e:
try:
response = urllib.request.urlopen(entry_link.encode('ascii', errors='xmlcharrefreplace').decode('ascii'))
print(
"opening the link did not work, try to encode to ascii replacing xmlcharrefs now and reopen - the original error message is:",
e,
)
except Exception as ex:
print(entry_link, entry_link.encode('ascii', errors='xmlcharrefreplace').decode('ascii'), ex )
try:
web_content = response.read().decode("UTF-8")
except Exception as e:
try:
web_content = response.read().decode("latin-1")
print(
"decoding the respone in utf8 did not work, try to decode latin1 now - the original error message is:",
e,
)
except Exception as ex:
print(ex)
# save interim results to files