Module: CoaOpScraper::Legacy

Defined in:
lib/legacy.rb

Class Method Summary collapse

Class Method Details

.parse_opinion_list(doc) ⇒ Object 



17
18
19
20
21
22
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
 
# File 'lib/legacy.rb', line 17

def self.parse_opinion_list(doc)
  data = Nokogiri::HTML.parse(doc)

  # Note: A quirk in Nokogiri - this TABLE is actually nested inside a P, but	 it's "correcting" the HTML
  # so... I'm relying on finding the relevant <P> and lining each next to the corresponding <TABLE>
  target_zone = data.search("#submission").search("p")								# Also contain the headers
  targets = target_zone.select { |t| t.inner_text.match(/Before/) }		# Focus just on opinion releases
  docket_targets = data.search("#submission").search("table")					# <TABLE> follows each

  # release date
  srd = data.search('#submission').search('p').first.inner_text.split("Opinions").last
  release_date = srd.strip_both_ends.to_date

  results = []
  targets.each_with_index do |t,i|
    next if docket_targets.count < (i + 1)
    # because can't complete the match at the end

    result = Hash.new
    opinions = t.search("a")

    result[:author_string] = opinions.first.inner_text.strip_both_ends
    result[:opinion_urls] = {}
    opinions.each do |op|
      text_part = op.inner_text.downcase
      href_target = op["href"]
      if href_target.downcase.match(/pdfopinion/) or text_part.match(/pdf/)
        result[:opinion_urls]["pdf"] = href_target
      elsif href_target.downcase.match(/htmlopinion/)
        result[:opinion_urls]["html"] = href_target
      elsif text_part.match(/wpd/)
        result[:opinion_urls]["wpd"] = href_target
      end
    end
    spans = t.search("span")
    result[:disposition] = spans.first.inner_text.strip_both_ends
    result[:panel_string] = t.search("b").inner_text.strip_both_ends

    result[:release_date] = release_date				

    source = docket_targets[i].search("td").last.inner_text
    parts = source.split("--")
    if parts.size == 2
      result[:case_style] = parts.first
      result[:origin] = parts.second
    elsif parts.size == 1
      result[:case_style] = parts.first
    end

    result[:docket_no] = docket_targets[i].search("a").inner_text
    result[:docket_page_url] = docket_targets[i].search("a").first["href"]
    # ensuring enough info to salvage if I need to
    next if result[:docket_no].nil? or result[:docket_page_url].nil?
    next if result[:docket_no].blank? or result[:docket_page_url].blank?
    results << result
  end
  results
end

.url_for_coa_for_date(coa, date) ⇒ Object 



11
12
13
14
15
 
# File 'lib/legacy.rb', line 11

def self.url_for_coa_for_date(coa,date)
  datestring = date.to_date.strftime("%Y%m%d")
  root_path = "http://www.#{coa.to_i.ordinalize}coa.courts.state.tx.us/"
  root_path + "opinions/docket.asp?FullDate=#{datestring}"
end