Skip to content

modify the last step of title-extracting #476

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Ckins wants to merge 2 commits into
base: master
Choose a base branch
from
Open

modify the last step of title-extracting #476

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8777c4b
add feature for title extract
Ckins Nov 24, 2017
84f3f73
enhance filter
Ckins Nov 29, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions newspaper/cleaners.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,12 @@ def __init__(self, config):
"|date|^print$|popup|author-dropdown|tools|socialtools|byline"
"|konafilter|KonaFilter|breadcrumbs|^fn$|wp-caption-text"
"|legende|ajoutVideo|timestamp|js_replies"
"|date|^print$|popup|author-dropdown|tools|socialtools|byline"
"|konafilter|KonaFilter|breadcrumbs|^fn$|wp-caption-text"
"|legende|ajoutVideo|timestamp|js_replies|breadcrumb|^rating$""|^comment$|^share$|^like$|^icon$|^count$|^sharing$|^news-list$"
"|^vote$|^ad$|^Ad$|^rec$|^oneindia$|^inread$|^showmore$|^tags_scroll$""|^Share$|^date$|^related$|^fb-root$|^recommendation$|^recomment$"
"|^readalso$|^read-also$|^image_counter$|^yarp$|^navig$|^extranews$""|^arrow$|^slider__footer$|^socbuttons$|^see-more$|^subscribe$"
"|post-data|post-social|article__content__author-title|archive__posts__item""|user|^banner$|^flair$|^forlo$|append-news|^inject$|^rg-gallery_inj$|^tag$"
)
self.regexp_namespace = "http://exslt.org/regular-expressions"
self.nauthy_ids_re = ("//*[re:test(@id, '%s', 'i')]" %
Expand Down
9 changes: 8 additions & 1 deletion newspaper/extractors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
import re
from collections import defaultdict

from difflib import SequenceMatcher
from dateutil.parser import parse as date_parser
from tldextract import tldextract
from urllib.parse import urljoin, urlparse, urlunparse
Expand Down Expand Up @@ -342,11 +343,17 @@ def get_title(self, doc):
# (either it differs for case, for special chars, or it's truncated)
# in these cases, we prefer the title_text_h1
filter_title = filter_regex.sub('', title).lower()
if filter_title_text_h1 == filter_title:
if self.is_similar(filter_title_text_h1, filter_title):
title = title_text_h1

return title

def is_similar(self, text_a, text_b):
"""used for comparison between the final title and title_text_h1
0.6 is an empirical value
"""
return SequenceMatcher(None, text_a, text_b).ratio() > 0.6

def split_title(self, title, splitter, hint=None):
"""Split the title to best part possible
"""
Expand Down