libcraigscrape 0.7.0 → 0.8.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (25) hide show
  1. data/CHANGELOG +19 -0
  2. data/README +27 -11
  3. data/Rakefile +44 -2
  4. data/bin/craig_report_schema.yml +30 -21
  5. data/bin/craigwatch +232 -67
  6. data/bin/report_mailer/craigslist_report.html.erb +12 -9
  7. data/bin/report_mailer/craigslist_report.plain.erb +4 -1
  8. data/lib/geo_listings.rb +144 -0
  9. data/lib/libcraigscrape.rb +158 -650
  10. data/lib/listings.rb +144 -0
  11. data/lib/posting.rb +293 -0
  12. data/lib/scraper.rb +203 -0
  13. data/test/geolisting_samples/hierarchy_test071009/index.html +31 -0
  14. data/test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/%20SW%20florida/index.html +46 -0
  15. data/test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/index.html +46 -0
  16. data/test/geolisting_samples/hierarchy_test071009/us/fl/index.html +46 -0
  17. data/test/geolisting_samples/hierarchy_test071009/us/fl/miami/index.html +46 -0
  18. data/test/geolisting_samples/hierarchy_test071009/us/fl/miami/nonsense/index.html +46 -0
  19. data/test/geolisting_samples/hierarchy_test071009/us/fl/miami/nonsense/more-nonsense/index.html +46 -0
  20. data/test/geolisting_samples/hierarchy_test071009/us/fl/nonexist/index.html +46 -0
  21. data/test/geolisting_samples/hierarchy_test071009/us/fl/nonsense/index.html +46 -0
  22. data/test/geolisting_samples/hierarchy_test071009/us/fl/south%20florida/index.html +46 -0
  23. data/test/geolisting_samples/hierarchy_test071009/us/index.html +355 -0
  24. data/test/test_craigslist_geolisting.rb +476 -380
  25. metadata +28 -2
data/test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/%20SW%20florida/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/ft%20myers%20%5C/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/miami/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/miami/nonsense/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/miami/nonsense/more-nonsense/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/nonexist/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/nonsense/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>
data/test/geolisting_samples/hierarchy_test071009/us/fl/south%20florida/index.html ADDED
@@ -0,0 +1,46 @@
1
+
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <title>craigslist: florida classifieds for jobs, apartments, personals, for sale, services, community, and events</title>
6
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7
+ <link rel="stylesheet" title="craigslist" href="http://www.craigslist.org/styles/craigslist.css" type="text/css" media="all">
8
+ <style type="text/css"><!--
9
+ a { text-decoration: none; }
10
+ #list { line-height: 1.40em;; }
11
+ #list em { font-size: smaller; font-weight: normal; }
12
+ -->
13
+ </style>
14
+ </head>
15
+ <body>
16
+ <blockquote>
17
+ <h3><b><a href="http://www.craigslist.org/">craigslist</a> &gt; florida</b> <sup><a href="http://en.wikipedia.org/wiki/florida">w</a></sup></h3>
18
+
19
+ <blockquote>&nbsp;
20
+ <blockquote>
21
+ <h4>choose the site nearest you (<a href="http://forums.craigslist.org/?forumID=1">or suggest a new one</a>):</h4>
22
+ <blockquote>&nbsp;
23
+ <div id="list"><a href="http://daytona.craigslist.org/">daytona beach</a> <br>
24
+ <a href="http://keys.craigslist.org/">florida keys</a> <br>
25
+ <a href="http://fortmyers.craigslist.org/">ft myers / SW florida</a> <br>
26
+ <a href="http://gainesville.craigslist.org/">gainesville</a> <br>
27
+ <a href="http://jacksonville.craigslist.org/">jacksonville</a> <br>
28
+ <a href="http://lakeland.craigslist.org/">lakeland</a> <br>
29
+ <a href="http://ocala.craigslist.org/">ocala</a> <br>
30
+ <a href="http://orlando.craigslist.org/"><b>orlando</b></a> <br>
31
+ <a href="http://panamacity.craigslist.org/">panama city</a> <br>
32
+ <a href="http://pensacola.craigslist.org/">pensacola / panhandle</a> <br>
33
+ <a href="http://sarasota.craigslist.org/">sarasota-bradenton</a> <br>
34
+ <a href="http://miami.craigslist.org/"><b>south florida</b></a> - includes separate sections for miami/dade, broward, and palm beach counties<br>
35
+ <a href="http://spacecoast.craigslist.org/">space coast</a> <br>
36
+ <a href="http://staugustine.craigslist.org/">st augustine</a> <br>
37
+ <a href="http://tallahassee.craigslist.org/">tallahassee</a> <br>
38
+ <a href="http://tampa.craigslist.org/"><b>tampa bay area</b></a> <br>
39
+ <a href="http://treasure.craigslist.org/">treasure coast</a> <br>
40
+ </div>
41
+ </blockquote>
42
+ </blockquote>
43
+ </blockquote>
44
+ </blockquote>
45
+ </body>
46
+ </html>