scraper.scala
changeset 7 73cf4406b773
parent 1 b606c9439fa6
equal deleted inserted replaced
6:0da19c346e24 7:73cf4406b773
    19 wr.close
    19 wr.close
    20 
    20 
    21 //receiving data
    21 //receiving data
    22 val page = fromInputStream(conn.getInputStream).getLines.mkString("\n")
    22 val page = fromInputStream(conn.getInputStream).getLines.mkString("\n")
    23 
    23 
    24 println(page)
    24 //println(page)
    25 
    25 
    26 // regular expression . excludes newlines, 
    26 // regular expression . excludes newlines, 
    27 // therefore we have to use [\S\s]
    27 // therefore we have to use [\S\s]
    28 val regex1 = """<tr align="center">[\S\s]*?</tr>""".r
    28 val regex1 = """<tr align="center">[\S\s]*?</tr>""".r
    29 val rows = regex1.findAllIn(page).toList
    29 val rows = regex1.findAllIn(page).toList
    30 
    30 
    31 print(rows)
    31 //print(rows)
    32 
    32 
    33 val regex2 = """<td align="center">([\S\s]*?)</td>""".r
    33 val regex2 = """<td align="center">([\S\s]*?)</td>""".r
    34 
    34 
    35 def aux(s: String) : Array[String] = {
    35 def aux(s: String) : Array[String] = {
    36   for (m <- regex2.findAllIn(s).toArray) yield m match {
    36   for (m <- regex2.findAllIn(s).toArray) yield m match {