20 lines
2.8 KiB
Python
20 lines
2.8 KiB
Python
|
|
import re
|
|
import json
|
|
|
|
s =['''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">丹·琼斯(Dan Jones)</span><span class="a-size-base" dir="auto">, </span><span class="a-size-base" dir="auto">杰弗里·瓦夫罗(Geoffrey Wawro)</span><span class="a-size-base" dir="auto">, </span><span class="a-size-base" dir="auto">克里斯托弗·希伯特(Christopher Hibbert)</span><span class="a-size-base" dir="auto">, </span><span class="a-size-base" dir="auto">罗斯·金(Ross King)</span><span class="a-size-base" dir="auto">等等。</span></div>''',
|
|
'''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">马克·哈里斯</span><span class="a-size-base" dir="auto">、 </span><span class="a-size-base" dir="auto">黎绮妮</span></div>''',
|
|
'''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">马克·哈里斯</span><span class="a-size-base" dir="auto">、 </span><span class="a-size-base" dir="auto">黎绮妮</span></div>''',
|
|
'''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">[美]威廉·厄本(William Urban)</span><span class="a-size-base" dir="auto">, </span><span class="a-size-base" dir="auto">陆大鹏</span><span class="a-size-base" dir="auto">、 </span><span class="a-size-base" dir="auto">刘晓晖</span></div>''',
|
|
'''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">[英]安德鲁·罗伯茨(Andrew Roberts)</span><span class="a-size-base" dir="auto">、 </span><span class="a-size-base" dir="auto">苏然</span></div>''',
|
|
'''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">[英]安德鲁·罗伯茨(Andrew Roberts)</span><span class="a-size-base" dir="auto">、 </span><span class="a-size-base" dir="auto">苏然</span></div>''',
|
|
'''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">堀田江理(Eri Hotta)</span></div>''',
|
|
'''<div class="a-row a-size-base a-color-secondary"><span class="a-size-base" dir="auto"></span><span class="a-size-base" dir="auto">景跃进</span><span class="a-size-base" dir="auto">, </span><span class="a-size-base" dir="auto">张小劲</span><span class="a-size-base" dir="auto">、 </span><span class="a-size-base" dir="auto">余逊达</span></div>''']
|
|
|
|
for t in s:
|
|
ret = re.split('<span.+?auto\">|<\/span',t)
|
|
fret = ret[3::4]
|
|
#print(json.dumps(re.split('<span.+?auto\">|<\/span',t), indent=2, ensure_ascii=False))
|
|
print(','.join(fret))
|
|
|