github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

pre-compile regex pattern for remove_html() and split_html()

Browse Source
This commit is contained in:
Mike Fährmann
2020-03-13 23:30:16 +01:00
parent fdd2dd5136
commit f6c5edb76b
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
gallery_dl/text.py
View File

@@ -15,6 +15,8 @@ import datetime
import urllib.parse import urllib.parse
HTML_RE = re.compile("<[^>]+>")
INVALID_XML_CHARS = ( INVALID_XML_CHARS = (
"\x00", "\x01", "\x02", "\x03", "\x04", "\x05", "\x06", "\x07", "\x00", "\x01", "\x02", "\x03", "\x04", "\x05", "\x06", "\x07",
"\x08", "\x0b", "\x0c", "\x0e", "\x0f", "\x10", "\x11", "\x12", "\x08", "\x0b", "\x0c", "\x0e", "\x0f", "\x10", "\x11", "\x12",
@@ -39,7 +41,7 @@ def clean_xml(xmldata, repl=""):
def remove_html(txt, repl=" ", sep=" "): def remove_html(txt, repl=" ", sep=" "):
"""Remove html-tags from a string""" """Remove html-tags from a string"""
try: try:
txt = re.sub("<[^>]+>", repl, txt) txt = HTML_RE.sub(repl, txt)
except TypeError: except TypeError:
return "" return ""
if sep: if sep:
@@ -51,7 +53,7 @@ def split_html(txt, sep=None):
"""Split input string by html-tags""" """Split input string by html-tags"""
try: try:
return [ return [
x.strip() for x in re.split("<[^>]+>", txt) x.strip() for x in HTML_RE.split(txt)
if x and not x.isspace() if x and not x.isspace()
] ]
except TypeError: except TypeError: