Class: WebAnalyticsDiscovery::MailRu

Inherits:
Object
  • Object
show all
Includes:
GrabberUtils
Defined in:
lib/web_analytics_discovery/grabber/mailru.rb

Constant Summary

Constants included from GrabberUtils

GrabberUtils::AVG_DAYS_IN_MONTH, GrabberUtils::CACHE_DIR, GrabberUtils::USER_AGENT

Instance Method Summary collapse

Methods included from GrabberUtils

#download, #download_file, #mangle_url

Instance Method Details

#find_id ⇒ Object 



14
15
16
17
18
19
20
21
22
23
24
 
# File 'lib/web_analytics_discovery/grabber/mailru.rb', line 14

def find_id
  case @page
  when /<a [^>]*href="http:\/\/top\.mail\.ru\/jump\?from=(\d+)".*>\s*<img src="http:\/\/.*.top.mail.ru\/counter/m,
    /<img src=['"]?http:\/\/top\.list\.ru\/counter\?id=(\d+)/,
    /<img src=['"]?http:\/\/.*top\.mail\.ru\/counter\?js=na;id=(\d+)/,
    /_tmr.push\(\{id:\s*['"](\d+)['"]/
    $1.to_i
  else
    nil
  end
end

#run(url) ⇒ Object 



9
10
11
12
 
# File 'lib/web_analytics_discovery/grabber/mailru.rb', line 9

def run(url)
  @page = download(url)
  run_id(find_id)
end

#run_id(id) ⇒ Object 



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
 
# File 'lib/web_analytics_discovery/grabber/mailru.rb', line 26

def run_id(id)
  return nil unless id
  r = {:id => id}

  #doc = download("http://top.mail.ru/visits?id=#{id}")

  # Analyze daily report
  doc = download("http://top.mail.ru/visits.csv?id=#{id}&period=0&date=&back=30&", 'windows-1251').split(/\n/)
  return run_id_html_rating(r, id) if doc.empty?
  doc = doc[4..-1]

  sum_v = 0
  sum_pv = 0
  doc.each { |l|
    #"Дата";"Посетители";"Новые посетители";"Ядро";"Хосты";"Просмотры";"Глубина"
    date, v, new_v, core_v, hosts, pv, depth = l.split(/;/)
    sum_v += v.to_i
    sum_pv += pv.to_i
  }

  r[:visitors_day] = sum_v / doc.size
  r[:pv_day] = sum_pv / doc.size

  # Analyze weekly report
  doc = download("http://top.mail.ru/visits.csv?id=#{id}&period=1&date=&back=98&", 'windows-1251').split(/\n/)
  return r if doc.empty?
  date, v, new_v, core_v, hosts, pv, depth = doc[4].split(/;/)
  r[:visitors_week] = v.to_i
  r[:pv_week] = pv.to_i

  # Analyze monthly report
  doc = download("http://top.mail.ru/visits.csv?id=#{id}&period=2&date=&back=395&", 'windows-1251').split(/\n/)
  return r if doc.empty?
  date, v, new_v, core_v, hosts, pv, depth = doc[4].split(/;/)
  r[:visitors_mon] = v.to_i
  r[:pv_mon] = pv.to_i

  return r
end

#run_id_html_rating(r, id) ⇒ Object

Parse semi-closed rating when normal full CSV export is not available



67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
 
# File 'lib/web_analytics_discovery/grabber/mailru.rb', line 67

def run_id_html_rating(r, id)
  doc = download("http://top.mail.ru/rating?id=#{id}", 'windows-1251')

  today = []
  doc.gsub(/<td class="l_col">Сегодня<\/td>.*?<td class="r_col"><b>([0-9,]+)<\/b>/m) { today << $1.gsub(/,/, '').to_i }

  week = []
  doc.gsub(/<td class="l_col">Неделя<\/td>.*?<td class="r_col"><b>([0-9,]+)<\/b>/m) { week << $1.gsub(/,/, '').to_i }

  month = []
  doc.gsub(/<td class="l_col">Месяц<\/td>.*?<td class="r_col"><b>([0-9,]+)<\/b>/m) { month << $1.gsub(/,/, '').to_i }

  # Non-normal number of matches? That's weird, bail out
  return r unless today.length == 3 and week.length == 3 and month.length == 3

  r[:visitors_day], r[:pv_day], r[:ip_day] = today
  r[:visitors_week], r[:pv_week], r[:ip_week] = week
  r[:visitors_mon], r[:pv_mon], r[:ip_mon] = month

  return r
end