Skip to content
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

Fix Funke topics #555

Merged
merged 4 commits into from
Jul 17, 2024
Merged

Fix Funke topics #555

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
bf2e9a7
update funke topics
addie9800 Jul 4, 2024
0c42142
replace split with sub
addie9800 Jul 16, 2024
84fd294
fix regexes
MaxDall Jul 17, 2024
988e45c
black
MaxDall Jul 17, 2024
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
10 changes: 9 additions & 1 deletion src/fundus/publishers/de/braunschweiger_zeitung.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ class V1(BaseParser):
" or contains(text(), 'Auch interessant')"
" or contains(text(), 'Weitere News'))]"
)
_topics_selector = XPath("//div[@class='not-prose mb-4 mx-5 font-sans']/ul/li")

@attribute
def body(self) -> ArticleBody:
Expand All @@ -44,7 +45,14 @@ def title(self) -> Optional[str]:

@attribute
def topics(self) -> List[str]:
return generic_topic_parsing(self.precomputed.meta.get("news_keywords"))
if topics := generic_topic_parsing(self.precomputed.meta.get("news_keywords")):
return topics
else:
pass
return [
re.sub(r"\s*–.+", "", node.text_content()).strip()
for node in self._topics_selector(self.precomputed.doc)
]

@attribute
def authors(self) -> List[str]:
Expand Down
11 changes: 10 additions & 1 deletion src/fundus/publishers/de/hamburger_abendblatt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
import datetime
import re
from typing import List, Optional

from lxml.cssselect import CSSSelector
from lxml.etree import XPath

from fundus.parser import ArticleBody, BaseParser, ParserProxy, attribute
from fundus.parser.utility import (
Expand All @@ -17,6 +19,7 @@ class V1(BaseParser):
_summary_selector = CSSSelector("div.article-body > p.font-sans")
_paragraph_selector = CSSSelector("div.article-body > p:not(.font-sans)")
_subheadline_selector = CSSSelector("div.article-body > h3")
_topics_selector = XPath("//div[@class='not-prose mb-4 mx-5 font-sans']/ul/li")

@attribute
def body(self) -> ArticleBody:
Expand All @@ -41,4 +44,10 @@ def title(self) -> Optional[str]:

@attribute
def topics(self) -> List[str]:
return generic_topic_parsing(self.precomputed.meta.get("keywords"))
if topics := generic_topic_parsing(self.precomputed.meta.get("keywords")):
return topics
else:
return [
re.sub(r"\s*–.+", "", node.text_content()).strip()
for node in self._topics_selector(self.precomputed.doc)
]
11 changes: 10 additions & 1 deletion src/fundus/publishers/de/morgenpost_berlin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
import datetime
import re
from typing import List, Optional

from lxml.cssselect import CSSSelector
from lxml.etree import XPath

from fundus.parser import ArticleBody, BaseParser, ParserProxy, attribute
from fundus.parser.utility import (
Expand All @@ -17,6 +19,7 @@ class V1(BaseParser):
_summary_selector = CSSSelector("div.article-body > p.font-sans.font-medium")
_paragraph_selector = CSSSelector("div.article-body > p:not([class])")
_subheadline_selector = CSSSelector("div.article-body > h3")
_topics_selector = XPath("//div[@class='not-prose mb-4 mx-5 font-sans']/ul/li")

@attribute
def body(self) -> ArticleBody:
Expand All @@ -41,4 +44,10 @@ def title(self) -> Optional[str]:

@attribute
def topics(self) -> List[str]:
return generic_topic_parsing(self.precomputed.meta.get("keywords"))
if topics := generic_topic_parsing(self.precomputed.meta.get("keywords")):
return topics
else:
return [
re.sub(r"\s*–.+", "", node.text_content()).strip()
for node in self._topics_selector(self.precomputed.doc)
]
12 changes: 10 additions & 2 deletions src/fundus/publishers/de/waz.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import datetime
import re
from typing import List, Optional

from lxml.cssselect import CSSSelector
Expand All @@ -19,6 +20,7 @@ class V1(BaseParser):
_paragraph_selector: XPath = CSSSelector(".article__body > p")
_summary_selector: XPath = CSSSelector(".article__header__intro__text")
_subheadline_selector: XPath = CSSSelector(".article__body > h3")
_topics_selector = XPath("//div[@class='not-prose mb-4 mx-5 font-sans']/ul/li")

@attribute
def body(self) -> ArticleBody:
Expand All @@ -44,8 +46,14 @@ def publishing_date(self) -> Optional[datetime.datetime]:
@attribute
def topics(self) -> List[str]:
authors = generic_author_parsing(self.precomputed.meta.get("author"))
topics = generic_topic_parsing(self.precomputed.meta.get("keywords"))
return [topic for topic in topics if topic not in authors]
if topics := generic_topic_parsing(self.precomputed.meta.get("keywords")):
return [topic for topic in topics if topic not in authors]
else:
pass
return [
re.sub(r"\s*:.+", "", node.text_content()).strip()
for node in self._topics_selector(self.precomputed.doc)
]

class V1_1(V1):
VALID_UNTIL = datetime.date.today()
Expand Down