from bs4 import BeautifulSoup
import urllib
import re
r = urllib.urlopen(
'http://forums.hardwarezone.com.sg/eat-drink-man-woman-16/%5Bofficial%5D-chit-chat-students-part-2-a-5526993-55.html').read()
soup = BeautifulSoup(r, "lxml")
letters = soup.find_all("div", attrs={"id":re.compile("post_message_\d+")})
for a in letters:
print [b.strip() for b in a.text.strip().split('\n') if b.strip()]
所有信息:
相关问题 更多 >
编程相关推荐