使用feedparser检测重复标题

Question

def parseRSS(rss_url):
    parsed_feed = feedparser.parse(rss_url)
    return parsed_feed

def getHeadlines(rss_url,key):
    headlines = []
    feed = parseRSS(rss_url)
    for newsitem in feed['items']:
        if newsitem['title'] not in headlines:
            headlines.append([newsitem,key])
        else:
            print("-----------------------Duplicate title found----------------------")
    return headlines

def get_rss():
    allheadlines = []
    newsurls = {
    ('key1','source1'): 'https://news.google.com/news/rss/?hl=en&ned=us&gl=US',
    ('key2','source2'): 'https://news.google.com/news/rss/?hl=en&ned=us&gl=US',
    }
    for key,url in newsurls.items():
        allheadlines.extend(getHeadlines(url,key))

    return allheadlines

allheadlines = get_rss()

for hl in allheadlines:
    source = hl[1][0]
    key = hl[1][1]
    title = hl[0]['title']
    link = hl[0]['link']

我使用相同的rss feed进行测试。每次添加新标题时，我都会检查标题是否已经在标题中。但是，它似乎没有检测到重复的标题。找到的重复标题永远不会被打印。我究竟做错了什么？

Answer 1

尝试一下

def parseRSS(rss_url):
    parsed_feed = feedparser.parse(rss_url)
    return parsed_feed

def getHeadlines(rss_url,key,allheadlines,allitems):
    feed = parseRSS(rss_url)
    for newsitem in feed['items']:
        if newsitem['title'] not in allheadlines:
            allheadlines.append(newsitem['title'])
            allitems.append([newsitem,key])
        else:
            print("-----------------------Duplicate title found----------------------")
    return allheadlines,allitems

def get_rss():
    allheadlines = []
    allitems = []
    newsurls = {
    ('key1','source1'): 'https://news.google.com/news/rss/?hl=en&ned=us&gl=US',
    ('key2','source2'): 'https://news.google.com/news/rss/?hl=en&ned=us&gl=US',
    }
    for key,url in newsurls.items():
        allheadlines,allitems=(getHeadlines(url,key,allheadlines,allitems))

    return allitems

allheadlines = get_rss()