re模块

import re
# 取出字符串string8中所有的天气状态
string8 = "{ymd:'2018-01-01',tianqi:'晴',aqiInfo:'轻度污染'}," \
          "{ymd:'2018-01-02',tianqi:'阴~小雨',aqiInfo:'优'}," \
          "{ymd:'2018-01-03',tianqi:'小雨~中雨',aqiInfo:'优'}," \
          "{ymd:'2018-01-04',tianqi:'中雨~小雨',aqiInfo:'优'}"

print(re.findall("tianqi:'(.{1,5})'", string8))
print(re.findall("tianqi:'(.*?)'", string8))

# 取出string9中所有含O字母的单词
string9 = 'Together, we discovered that a free market only ' \
           'thrives when there are rules to ensure competition ' \
           'and fair play, Our celebration of initiative and enterprise'

print(re.findall("(\w*o\w*)", string9, flags=re.I))
print(re.findall('\w*o\w*',string9, flags = re.I))

# 将string10中的标点符号、数字和字母删除
string10 = '据悉，这次发运的4台蒸汽冷凝罐属于国际热核聚变实验堆（ITER）' \
           '项目的核二级压力设备，先后完成了压力试验、真空试验、氦气检漏试验、' \
           '千斤顶试验、吊耳载荷试验、叠装试验等验收试验。'

print(re.sub('[\W*A-Z0-9]', '', string10))
print(re.sub('[，。、a-zA-Z0-9（）]', '', string10))

# 将string11中的每个子部分内容分割开
string11 = '2室2厅 | 101.62平 | 低区/7层 | ' \
           '朝南 \n 上海未来 - 浦东 - 金杨 - 2005年建'

print(re.split('[-\|\n]', string11))

split = re.split('[-\|\n]', string11)
print(split)
# 分割结果的清洗
split_strip = [i.strip() for i in split]
print(split_strip)