url = 'http://www.millercenter.org/president/speeches'
conn = urllib2.urlopen(url)
html = conn.read()
miller_center_soup = BeautifulSoup(html)
links = miller_center_soup.find_all('a')
linklist = [tag.get('href') for tag in links if tag.get('href') is not None]
linklist = str(linklist)
end_of_links = [line for line in linklist if '/events/' in line]
print end_of_links
这是我输出的一小部分（保存在Python列表中）。
['/events/2015/one-nation-under-god-how-corporate-america-invented-christian-america',
'/events/2015/a-conversation-with-bernie-sanders', '#reagan', '#gwbush', '#obama',
'#top', '/president/obama/speeches/speech-4427', president/obama/speeches/speech-4430', ...]
我想删除列表中不包含speeches的所有项目。我已经尝试了filter()并且只创建了另一个列表理解，但这还没有奏效。我不知道为什么end_of_links变量不起作用 - 至少对我来说似乎很直观。
答案 0 :(得分：1)
li = ['/ events / 2015 / one-nation-under-god-how-corporate-america-invented-christian-america'， '/ events / 2015 / a-conversation-with-bernie-sanders'，'#reagan'，'＃gwbush'，'＃obama'， '#top'，'/ president / obama / speeches / speech-4427'，'president / obama / speeche / speech-4430']
导入重新
li = [x for li in li if re.search（'speeches'，x）]
打印（LI）
['/ president / obama / speeches / speech-4427'，'president / obama / speeches / speech-4430']
答案 1 :(得分：0)
Kust保留做包括'演讲'的那些：
link_list = ['/events/2015/one-nation-under-god-how-corporate-america-invented-christian-america',
'/events/2015/a-conversation-with-bernie-sanders', '#reagan', '#gwbush', '#obama',
'#top', '/president/obama/speeches/speech-4427', 'president/obama/speeches/speech-4430']
speech_list = [_ for _ in link_list if 'speeches' in _]
这是我在Python2.7中的终端会话
>>> link_list = ['/events/2015/one-nation-under-god-how-corporate-america-invented-christian-america',
... '/events/2015/a-conversation-with-bernie-sanders', '#reagan', '#gwbush', '#obama',
... '#top', '/president/obama/speeches/speech-4427', 'president/obama/speeches/speech-4430']
>>> speech_list = [_ for _ in link_list if 'speeches' in _]
>>> speech_list
['/president/obama/speeches/speech-4427', 'president/obama/speeches/speech-4430']
>>>