pjht/buku
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Override feed(), remove redundant API to reset parser.

Browse Source
This commit is contained in:
Arun Prakash Jana 2016-11-13 00:02:38 +05:30
parent 299d95aa45
commit 32b25e3d4f
No known key found for this signature in database
GPG Key ID: A75979F35C080412
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
buku.py
View File

@ -56,7 +56,8 @@ http_handler = None # urllib3 PoolManager handler
htmlparser = None # Use a single HTML Parser instance
# Disguise as Firefox on Ubuntu
USER_AGENT = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:48.0) Gecko/20100101 Firefox/48.0'
USER_AGENT = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:48.0) Gecko/20100101 \
Firefox/48.0'
# Crypto globals
BLOCKSIZE = 65536
@ -80,11 +81,12 @@ class BMHTMLParser(HTMLParser.HTMLParser):
self.prev_tag = None
self.parsed_title = None
def reinit(self):
def feed(self, data):
self.in_title_tag = False
self.data = ''
self.prev_tag = None
self.parsed_title = None
HTMLParser.HTMLParser.feed(self, data)
def handle_starttag(self, tag, attrs):
self.in_title_tag = False
@ -1470,8 +1472,6 @@ def get_page_title(resp):
if not htmlparser:
htmlparser = BMHTMLParser()
else:
htmlparser.reinit()
try:
htmlparser.feed(resp.data.decode(errors='replace'))