jerry/OpenBB
1
0
Fork 0
mirror of https://github.com/OpenBB-finance/OpenBB.git synced 2026-11-12 12:22:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

patching news with comments (#2530)

Browse Source 
adds functionality to keep runnings news until data is received. stops after 60 tries
This commit is contained in:
James Simmons
2022-09-13 10:41:37 -04:00
committed by GitHub
parent e3b4ff5e7c
commit 43dd40a8ee
1 changed files with 37 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
openbb_terminal/common/feedparser_model.py
View File

@@ -3,6 +3,7 @@ __docformat__ = "numpy"
import feedparser
import pandas as pd
from openbb_terminal.rich_config import console
def get_news(
@@ -23,25 +24,42 @@ def get_news(
articles : dict
term to search on the news articles
"""
if term:
if sources:
data = feedparser.parse(
f"https://news.google.com/rss/search?q={term}&hl=en-US&gl=US&ceid=US:en&when:24h+allinurl"
f':{sources.replace(" ", "%20")}'
)
have_data = False
console.print("[yellow]Fetching data. Please be patient\n[/yellow]")
limit = 0
while not have_data:
if term:
if sources:
data = feedparser.parse(
f"https://news.google.com/rss/search?q={term}&hl=en-US&gl=US&ceid=US:en&when:24h+allinurl"
f':{sources.replace(" ", "%20")}'
)
else:
data = feedparser.parse(
f"https://news.google.com/rss/search?q={term}&when:24h&hl=en-US&gl=US&ceid=US:en"
)
else:
data = feedparser.parse(
f"https://news.google.com/rss/search?q={term}&when:24h&hl=en-US&gl=US&ceid=US:en"
)
else:
if sources:
data = feedparser.parse(
f'https://news.google.com/rss/search?q=when:24h+allinurl:{sources.replace(" ", "%20")}'
"&hl=en-US&gl=US&ceid=US:en"
)
else:
data = feedparser.parse(
"https://news.google.com/rss/search?q=when:24h&hl=en-US&gl=US&ceid=US:en"
)
if sources:
data = feedparser.parse(
f'https://news.google.com/rss/search?q=when:24h+allinurl:{sources.replace(" ", "%20")}'
"&hl=en-US&gl=US&ceid=US:en"
)
else:
data = feedparser.parse(
"https://news.google.com/rss/search?q=when:24h&hl=en-US&gl=US&ceid=US:en"
)
if data.status == 200: # Checking if data request succeeded
if data.entries:
have_data = True
elif limit == 60: # Breaking if 60 successful requests return no data
console.print("[red]Timeout occurred. Please try again\n[/red")
break
limit = limit + 1
elif data.status != 200: # If data request failed
console.print("[red]Status code not 200. Unable to retrieve data\n[/red]")
break
return pd.DataFrame(data.entries, columns=["title", "link", "published"])