pageDownloader overhaul

This commit is contained in:
Fierelier 2021-03-20 16:41:10 +01:00
parent b7158c6a07
commit 09e9adc3e7

View File

@ -1,27 +1,26 @@
global urllib
import urllib.request
global html
import html
global downloadPage
def downloadPage(url,headers = False):
if not headers: headers = {}
request = urllib.request.Request(url,headers=headers)
response = None
try:
response = urllib.request.urlopen(request)
except urllib.error.HTTPError as e:
response = e
# process headers
headers = response.getheaders()
headersOut = {}
for hl in headers:
headersOut[hl[0]] = hl[1]
out = {
response = {
"url": url,
"headers": headersOut,
"body": response.read()
"body": None,
"headers": []
}
request = urllib.request.Request(url,headers=headers)
requestHandler = None
try:
requestHandler = urllib.request.urlopen(request)
response["headers"] = requestHandler.getheaders()
response["body"] = requestHandler.read()
except urllib.error.HTTPError as e:
response["body"] = e.read()
except Exception as e:
response["body"] = html.escape(e)
return out
return response