python爬虫各种日期格式解析

493次阅读
没有评论
python爬虫各种日期格式解析

爬虫时遇到的日期格式太多,统计一下日期的格式:

2018-6-21、2018年6月21、2018/6/21、21st Jun,2018、Jun 21st,2018(如果是其他月份还有缩写的形式)、Jun 21,2018、21-22 Jun 2018、Jun 21-22,2018、Thursday,21 Jun 2018(星期也可能会有缩写),还有未收录为了将日期格式统一,就需要解析。而网上的教程太少,就自己慢慢积累了。

import re

class DateFormatHelper(object): regex1 = re.compile(r"[0-9]{1,2}-[0-9]{1,2} *[A-Za-z]+ *[0-9]{4}") regex2 = re.compile(r"[0-9]{1,2} *[A-Za-z]+ *[0-9]{4}") regex3 = re.compile(r"[0-9]{4}-[0-9]{1,2}-[0-9]{1,2}") regex4 = re.compile(r"[A-Za-z]+ *[0-9]{1,2}, *[0-9]{4}") regex5 = re.compile(r"[A-Za-z]+ *[0-9]{1,2}-[0-9]{1,2}, *[0-9]{4}") regex6 = re.compile(r"[0-9]{4}年[0-9]{1,2}月[0-9]{1,2}日") dateformatregexs = [regex1, regex2, regex3, regex4, regex5, regex6]

monthMap = {"sep": "9", "oct": "10", "nov": "11", "dec": "12", "jan": "1", "feb": "2", "aug": "8", "jul": "7", "jun": "6", "may": "5", "apr": "4", "mar": "3"} monthMap2 = {"September": "9", "October": "10", "November": "11", "December": "12", "January": "1", "February": "2", "August": "8", "July": "7", "June": "6", "May": "5", "April": "4", "March": "3"} @classmethod def convertStandardDateFormat(cls, datestr: str) -> str: """ 转换日期格式 :param datestr: :return: """ res = "" if datestr is None: return res for i in range(0, len(cls.dateformatregexs)): try: regex = cls.dateformatregexs[i] match = regex.match(datestr) if match is not None: itemstr = match.group() if i == 0: items = str(itemstr).split(" ") year = items[len(items) – 1] month = cls.monthMap.get(str(items[1]).lower()) if month is None: month = cls.monthMap2.get(str(items[1])) dayrange = str(items[0]) day = dayrange[0:dayrange.index("-")] day2 = dayrange[dayrange.index("-") + 1:] res = year + "-" + month + "-" + day # res2 = year + "-" + month + "-" + str(day2) elif i == 1: items = str(itemstr).split(" ") year = items[len(items) – 1] month = cls.monthMap.get(str(items[1]).lower()) if month is None: month = cls.monthMap2.get(str(items[1])) day = items[0] res = year + "-" + month + "-" + day elif i == 3: items = str(itemstr).split(" ") year = items[len(items) – 1] month = cls.monthMap.get(str(items[0]).lower()) if month is None: month = cls.monthMap2.get(str(items[0])) digit_pattern = re.compile(r'[0-9]+') digitlist = digit_pattern.findall(items[1]) day = digitlist[0] res = year + "-" + month + "-" + day elif i == 4: items = str(itemstr).split(" ") year = items[len(items) – 1] month = cls.monthMap.get(str(items[0]).lower()) if month is None: month = cls.monthMap2.get(str(items[0])) dayrange = str(items[1]) day = dayrange[0:dayrange.index("-")] # day2 = dayrange[dayrange.index("-")+1:dayrange.index(",")] res = year + "-" + month + "-" + day # res2 = year + "-" + month + "-" + day2 elif i == 5: for x in range(len(str(itemstr))): if ord(itemstr[x]) > 255: itemstr = itemstr.replace(itemstr[x], " ") items = str(itemstr).split(" ") year = items[0] month = items[1] day = items[2] res = year + "-" + month + "-" + day else: res = datestr print(res) break except Exception as e: print("convertStandardDateFormat方法出现异常{}".format(e)) return res

注释没有怎么写,不,没写注释,这个习惯在改。就说说思路好了,将一个日期格式的字符串传递给 convertStandardDateFormat()

这个函数,当然准确的说是需要时调用这个classmethod函数。然后,这个函数就会识别日期字符串符合哪种规定日期格式。之后就好办啦,知道哪个是年哪个是月哪个是日,然后就很简单的替换赋值的就成了。嗯,这个程序目前才只能解析寥寥几个格式,所以就放到网上,希望看到的人能继续解析,如果可以就在哪里回复你们写的解析程序的地址,我去转载过来继续完善。新手上路,有问题建议就留言什么的,不要喷啊…

神龙|纯净稳定代理IP免费测试>>>>>>>>天启|企业级代理IP免费测试>>>>>>>>IPIPGO|全球住宅代理IP免费测试

相关文章:

版权声明:Python教程2022-10-28发表,共计2891字。
新手QQ群:570568346,欢迎进群讨论 Python51学习