string =“http://www.youtube.com/watchv=ClkQA2Lb_iE.......https://www.youtube.com/watch?v=ClkQA2Lb_iE，eeeeeee .www.youtube.com / watch？v = ClkQA2Lb_iE / vvvvvvvvvvvv --- websitename.com:1234/dir/file.txt”
我如何提取http://www.youtube.com,https://www.youtube.com,www.youtube.com,websitename.com
答案 0 :(得分：0)
import re
s = 'http://www.youtube.com/watch?v=ClkQA2Lb_iE.......https://www.youtube.com/watch?v=ClkQA2Lb_iE, eeeeeee.www.youtube.com/watch?v=ClkQA2Lb_iE/vvvvvvvvvvv---websitename.com:1234/dir/file.txt'
sp2=re.findall(r'https?://+[\w.]+[\w.]|www+[\w.]+[\w.]|[\w]+[\w.](?:com)', str(s))
print sp2