snegov/nevernote
1
0
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

add gzip support

Browse Source
This commit is contained in:
Maks Snegov 2014-06-17 22:31:02 +04:00
parent 2666d7911a
commit ae4a9b986e
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
nevernote.py
View File

@ -5,6 +5,7 @@ import http.client
import html.parser import html.parser
import sys import sys
from urllib.parse import urlparse from urllib.parse import urlparse
import zlib
class TitleParser(html.parser.HTMLParser): class TitleParser(html.parser.HTMLParser):
@ -52,12 +53,20 @@ def get_page(url):
if not c_type.startswith('text'): if not c_type.startswith('text'):
raise ValueError('incorrect Content-Type for HTML page: %s' % c_type) raise ValueError('incorrect Content-Type for HTML page: %s' % c_type)
c_encoding = response.getheader('Content-Encoding')
if c_encoding:
if c_encoding == 'gzip':
page_binary = zlib.decompress(response.read(), 16+zlib.MAX_WBITS)
else:
raise NotImplementedError(
'content encoding %s is not implemented' % c_encoding)
else:
page_binary = response.read()
charset = 'iso-8859-1' charset = 'iso-8859-1'
ct_spl = c_type.split('; ') ct_spl = c_type.split('; ')
if len(ct_spl) > 1: if len(ct_spl) > 1:
charset = ct_spl[1].split('=')[1] charset = ct_spl[1].split('=')[1]
page_binary = response.read()
page = page_binary.decode(charset) page = page_binary.decode(charset)
return page return page