Class: String

Inherits:
Object show all
Defined in:
lib/http_crawler/common/string.rb

Instance Method Summary collapse

Instance Method Details

#jagger_del_interObject

清除干扰数据清除包含: 空格,回车



5
6
7
# File 'lib/http_crawler/common/string.rb', line 5

def jagger_del_inter
  self.gsub(/(?:\n|\t|\r| | | |)/, "")
end

#jagger_to_arrayObject

创建时间: 2019/5/6 18:11 更新时间: 2019/5/6 作者: Jagger 方法名称: jagger_to_array 方法说明: 字符串分割成数组调用方式: #jagger_to_array

Returns:

  • Array



18
19
20
# File 'lib/http_crawler/common/string.rb', line 18

def jagger_to_array
  self.split(/(?:\n|\t|\r| | | )+/)
end

#jagger_to_timeObject

转换成时间格式



23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
# File 'lib/http_crawler/common/string.rb', line 23

def jagger_to_time

  # 然后先遍历所有格式
  # 模糊匹配格式,放前面的优先匹配
  # 如果 "%Y年%m月%d日%H:%M" 在 "%Y年%m月%d日%H:%M:%S" 前面
  # 则 "2018年01月01日12:01:30".jagger_to_time => 2018-01-01 12:01:00 +0800
  # 秒会被去掉
  [
      "%Y年%m月%d日%H:%M:%S",
      "%Y年%m月%d日%H:%M",


      "%Y年%m月%d日 %H:%M:%S",
      "%Y年%m月%d日 %H:%M",

      "%Y-%m-%d %H:%M:%S",
      "%Y-%m-%d %H:%M",

      "%Y-%m-%d%H:%M:%S",
      "%Y-%m-%d%H:%M",

      "%Y%m%d%H%M%S",
      "%Y%m%d%H%M",

      "%m月%d日 %H%M%S",
      "%m月%d日 %H%M",

      "%m月%d日%H%M%S",
      "%m月%d日%H%M",

      "%m月%d日 %H:%M:%S",
      "%m月%d日 %H:%M",

      "%m月%d日%H:%M:%S",
      "%m月%d日%H:%M",

      "%Y-%m-%d",
      "%Y%m%d",

      "%Y年%m月%d日",
      "%Y.%m.%d",

      "%Y年%m月",
      "%m月%d日",

      "%Y/%m/%d",
      "%Y/%m",

  ].each do |v|
    begin
      return Time.strptime(self, v)
    rescue => error

    end
  end

  case self
  when /^\d分钟前$/
    num = self[/^(\d)分钟前$/, 1].to_i
    return Time.now - num.minute
  when /^\d小时前$/
    num = self[/^(\d)小时前$/, 1].to_i
    return Time.now - num.hour
  when /^\d天前$/
    num = self[/^(\d)天前$/, 1].to_i
    return Time.now - num.day
  when /^\d年前$/
    num = self[/^(\d)年前$/, 1].to_i
    return Time.now - num.year
  end

  return Time.at(self.to_i / 1000.0) if self.length == 13
  return Time.at(self.to_i) if self.length == 10

  # 最后用 Time通用类型尝试
  return Time.parse(self)
end