开发者

create xml file from LIST file format

开发者 https://www.devze.com 2023-01-29 16:31 出处:网络
I ha开发者_StackOverflow社区ve downloaded some .LIST file from imdb database, and I wanna use them for some social network analyses reason (research with references), using a SNA software (where input

I ha开发者_StackOverflow社区ve downloaded some .LIST file from imdb database, and I wanna use them for some social network analyses reason (research with references), using a SNA software (where input can be in xml or csv)...


These libraries may help you:

http://libimdb.sourceforge.net/

http://libimdb.cvs.sourceforge.net/viewvc/libimdb/

https://trac.neo4j.org/browser/examples/imdb/trunk/src/main/java/org/neo4j/examples/imdb/parser?rev=2559


Here's something relevant I cooked up : A sed file 'movies2xml.sed':

# ampersand etc ..
s|&|\&|g
s|<|\&lt;|g
s|>|\&gt;|g
# last field, if range
s|\([12\?][0189\?][0-9\?][0-9\?]\)-\([12\?][0189\?][0-9\?][0-9\?]\)$|<when><f>\1</f><t>\2</t></when>|
# last field, if single
s|\([12?][0189?][0-9?][0-9?]\)$|<when><y>\1</y></when>|
# made-for tv/vid/vidgame ..
s|(\([TVG][TVG]*\)) *<when|<for>\1</for><when|
# episode
s|{\(.*\)} *|<ep>\1</ep>|
# ep season, number
s|<ep>\(.*\)(#\([0-9][0-9]*\)\.\([0-9][0-9]*\))</ep>|<ep s='\2' e='\3'>\1</ep>|
# release year / Number (when titles are duplicated in a year)
s| (\([12\?][0189\?][0-9\?][0-9\?]\)\/*\([IVX]*\)) <|<y N='\2'>\1</y><|
s|<y N=''>|<y>|
# TV titles
s|^"\([^<]*\)"<y|<title type='tvseries'>\1</title><y|
# titles
s|^\(.[^<]*\)<y|<title type='film'>\1</title><y|
# vid game
s| type='film'\(.*<for>VG<\)| type='videogame'\1|
# wrap tag
s|^\(<.*>\)$|<entry>\1</entry>|
# rm other text
s|^\([^<].*\)$|<!-- \1 -->|

The xml tagnames are a little terse, but (in june '14) there's 2,936,679 entries, which makes up 334MB ..

I process the imdb zip-file like this:

( F=movies.xml ; echo '<list>' > $F ; \
zcat movies.list.gz | \
    tr '\t' ' ' | tr -s  ' -' | recode l9..u8..xml | \
    sed -f movies2xml.sed >> $F ;  \
echo '</list>' >> $F ; ) &

This xml output then validates with this XSD :

<?xml version="1.0" encoding="UTF-8"?>
<!-- imdb_movies_list.xsd -->
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
  <xs:element name="list">
    <xs:complexType>
      <xs:sequence>
        <xs:element minOccurs="0" maxOccurs="unbounded" ref="entry"/>
      </xs:sequence>
    </xs:complexType>
  </xs:element>
  <xs:element name="entry">
    <xs:complexType>
      <xs:sequence>
        <xs:element minOccurs="1" maxOccurs="1" ref="title"/>
        <xs:element minOccurs="1" maxOccurs="1" ref="y"/>
        <xs:choice>
          <xs:element minOccurs="0" maxOccurs="1" ref="for"/>
          <xs:element minOccurs="0" maxOccurs="1" ref="ep"/>
        </xs:choice>
        <xs:element minOccurs="1" maxOccurs="1" ref="when"/>
      </xs:sequence>
    </xs:complexType>
  </xs:element>
  <xs:element name="title">
    <xs:complexType mixed="true">
      <xs:attribute name="type" use="required">
        <xs:simpleType>
          <xs:restriction base="xs:token">
            <xs:enumeration value="tvseries"/>
            <xs:enumeration value="videogame"/>
            <xs:enumeration value="film"/>
          </xs:restriction>
        </xs:simpleType>
      </xs:attribute>
    </xs:complexType>
  </xs:element>
  <xs:element name="y">
    <xs:complexType>
      <xs:simpleContent>
        <xs:extension base="yeartype">
          <xs:attribute name="N" use="optional">
            <xs:simpleType>
              <xs:restriction base="xs:token">
            <xs:enumeration value="I"/>
            <xs:enumeration value="II"/>
            <xs:enumeration value="III"/>
            <xs:enumeration value="IV"/>
            <xs:enumeration value="V"/>
            <xs:enumeration value="VI"/>
            <xs:enumeration value="VII"/>
            <xs:enumeration value="VIII"/>
            <xs:enumeration value="IX"/>
            <xs:enumeration value="X"/>
            <xs:enumeration value="XI"/>
            <xs:enumeration value="XII"/>
            <xs:enumeration value="XIII"/>
            <xs:enumeration value="XIV"/>
            <xs:enumeration value="XV"/>
            <xs:enumeration value="XVI"/>
            <xs:enumeration value="XVII"/>
            <xs:enumeration value="XVIII"/>
            <xs:enumeration value="XIX"/>
            <xs:enumeration value="XX"/>
            <xs:enumeration value="XXI"/>
            <xs:enumeration value="XXII"/>
            <xs:enumeration value="XXIII"/>
            <xs:enumeration value="XXIV"/>
            <xs:enumeration value="XXV"/>
            <xs:enumeration value="XXVI"/>
            <xs:enumeration value="XXVII"/>
            <xs:enumeration value="XXVIII"/>
            <xs:enumeration value="XXIX"/>
              </xs:restriction>
            </xs:simpleType>
          </xs:attribute>
        </xs:extension>
      </xs:simpleContent>
    </xs:complexType>
  </xs:element>
  <xs:element name="for">
    <xs:simpleType>
      <xs:restriction base="xs:token">
        <xs:enumeration value="TV"/>
        <xs:enumeration value="V"/>
        <xs:enumeration value="VG"/>
      </xs:restriction>
    </xs:simpleType>
  </xs:element>
  <xs:element name="ep">
    <xs:complexType mixed="true">
      <xs:attribute name="s" type="xs:integer" use="optional"/>
      <xs:attribute name="e" type="xs:integer" use="optional"/>
    </xs:complexType>
  </xs:element>
  <xs:element name="when">
    <xs:complexType>
      <xs:choice>
        <xs:sequence>
          <xs:element name="y" type="yeartype" minOccurs="1" maxOccurs="1"/>
        </xs:sequence>
        <xs:sequence>
          <xs:element name="f" type="yeartype" minOccurs="1" maxOccurs="1"/>
          <xs:element name="t" type="yeartype" minOccurs="1" maxOccurs="1"/>
        </xs:sequence>
      </xs:choice>
    </xs:complexType>
  </xs:element>
  <xs:simpleType name="yeartype">
    <xs:restriction base="xs:string">
      <xs:pattern value="[12?][0189?][0-9?][0-9?]"/>
    </xs:restriction>
  </xs:simpleType>
</xs:schema>

I expect there's an xml-to-json converter out there somewhere, for the believers ..

0

精彩评论

暂无评论...
验证码 换一张
取 消

关注公众号