Skip to content

allow custom content_extractore #152

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

Closed
itech001 wants to merge 2 commits into from
Closed

allow custom content_extractore #152

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
40f4b27
allow custom content_extractore
itech001 Jul 11, 2015
92b68e5
to support custom content extractor
itech001 Jul 12, 2015
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
3 changes: 3 additions & 0 deletions newspaper/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,9 @@
popular_urls, NewsPool, Configuration as Config)
from .source import Source
from .version import __version__
from .extractors import ContentExtractor
from .parsers import Parser
from .network import get_html

@yprez yprez Jan 18, 2016

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why add imports here?


news_pool = NewsPool()

Expand Down
8 changes: 6 additions & 2 deletions newspaper/article.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,14 +33,17 @@ class ArticleException(Exception):
class Article(object):
"""Article objects abstract an online news article page
"""
def __init__(self, url, title='', source_url='', config=None, **kwargs):
def __init__(self, url, title='', source_url='', config=None, content_extractor=None, **kwargs):
"""The **kwargs argument may be filled with config values, which
is added into the config object
"""
self.config = config or Configuration()
self.config = extend_config(self.config, kwargs)

self.extractor = ContentExtractor(self.config)
if content_extractor is None:
self.extractor = ContentExtractor(self.config)
else:
self.extractor = content_extractor

if source_url == '':
source_url = urls.get_scheme(url) + '://' + urls.get_domain(url)
Expand Down Expand Up @@ -212,6 +215,7 @@ def parse(self):

text = ''
self.top_node = self.extractor.calculate_best_node(self.doc)
#self.top_node = document_cleaner.clean(self.top_node)
if self.top_node is not None:
video_extractor = VideoExtractor(self.config, self.top_node)
self.set_movies(video_extractor.get_videos())
Expand Down
2 changes: 1 addition & 1 deletion newspaper/cleaners.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ def clean(self, doc_to_clean):
self.facebook_braodcasting_re)
doc_to_clean = self.remove_nodes_regex(doc_to_clean, self.twitter_re)
doc_to_clean = self.clean_para_spans(doc_to_clean)
doc_to_clean = self.div_to_para(doc_to_clean, 'div')
#doc_to_clean = self.div_to_para(doc_to_clean, 'div')
doc_to_clean = self.div_to_para(doc_to_clean, 'span')
return doc_to_clean

Expand Down
1 change: 1 addition & 0 deletions newspaper/outputformatters.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ def get_formatted(self, top_node):
self.remove_trailing_media_div()
text = self.convert_to_text()
# print(self.parser.nodeToString(self.get_top_node()))
#print(text)
return (text, html)

def convert_to_text(self):
Expand Down