SHOW:
|
|
- or go back to the newest paste.
| 1 | <configuration> | |
| 2 | <property> | |
| 3 | <name>http.agent.name</name> | |
| 4 | <value>My Nutch Spider</value> | |
| 5 | </property> | |
| 6 | ||
| 7 | <property> | |
| 8 | <name>http.accept.language</name> | |
| 9 | <value>zh-cn, en-us,en-gb,en;q=0.7,*;q=0.3</value> | |
| 10 | <description>Value of the “Accept-Language” request header field. This allows selecting non-English language as default one to retrieve. It is a useful setting for search engines build for certain national group. | |
| 11 | </description> | |
| 12 | </property> | |
| 13 | ||
| 14 | <property> | |
| 15 | <name>parser.character.encoding.default</name> | |
| 16 | <value>utf-8</value> | |
| 17 | <description>The character encoding to fall back to when no other information is available</description> | |
| 18 | </property> | |
| 19 | - | </configuration> |
| 19 | + | </configuration> |
| 20 | ||
| 21 | <regex> | |
| 22 | <pattern>\s</pattern> | |
| 23 | <substitution>%20</substitution> | |
| 24 | </regex> | |
| 25 | ||
| 26 | <property> | |
| 27 | <name>plugin.includes</name> | |
| 28 | <value>protocol-http|urlfilter-regex|parse-(html|tika|text)|index-(basic|anchor|more)|query-(basic|site|url)|response-(json|xml)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value> | |
| 29 | </property> | |
| 30 | ||
| 31 | <property> | |
| 32 | <name>http.content.size</name> | |
| 33 | <value>-1</value> | |
| 34 | </property> | |
| 35 | ||
| 36 | <property> | |
| 37 | <name>file.content.size</name> | |
| 38 | <value>-1</value> | |
| 39 | </property> | |
| 40 | ||
| 41 | <property> | |
| 42 | <name>http.content.limit</name> | |
| 43 | <value>-1</value> | |
| 44 | </property> | |
| 45 | ||
| 46 | <property> | |
| 47 | <name>file.content.limit</name> | |
| 48 | <value>-1</value> | |
| 49 | </property> | |
| 50 | ||
| 51 | <property> | |
| 52 | <name>parser.skip.truncated</name> | |
| 53 | <value>false</value> | |
| 54 | </property> | |
| 55 | ||
| 56 | <mimeType name="application/pdf"> | |
| 57 | <plugin id="parse-tika"/> | |
| 58 | </mimeType> |