pictuga
/
morss
1
1
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

readabilite: fix iter while iterating

master
pictuga 2017-03-19 01:56:33 -10:00
parent e65c88abf8
commit 4a5150e030
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
morss/readabilite.py
View File

@ -104,18 +104,21 @@ def get_best_node(root):
def clean_html(root): def clean_html(root):
for item in root.iter(): for item in list(root.iter()): # list() needed to be able to remove elements while iterating
# Step 1. Do we keep the node? # Step 1. Do we keep the node?
if item.tag in tags_junk: if item.tag in tags_junk:
item.getparent().remove(item) item.getparent().remove(item)
continue
class_id = item.get('class', '') + item.get('id', '') class_id = item.get('class', '') + item.get('id', '')
if regex_bad.match(class_id) is not None: if regex_bad.match(class_id) is not None:
item.getparent().remove(item) item.getparent().remove(item)
continue
if isinstance(item, lxml.html.HtmlComment): if isinstance(item, lxml.html.HtmlComment):
item.getparent().remove(item) item.getparent().remove(item)
continue
# Step 2. Clean the node's attributes # Step 2. Clean the node's attributes
@ -125,7 +128,7 @@ def clean_html(root):
def br2p(root): def br2p(root):
for item in root.iterfind('.//br'): for item in list(root.iterfind('.//br')):
parent = item.getparent() parent = item.getparent()
if parent is None: if parent is None:
continue continue