Hello everyone,
for a university project we have downloaded data with the operator "Crawl Web" and now we want to store it in the repository. This works wonderfully.
Unfortunately I can't retrieve this data in my subsequent RM process. The following error message always appears:
I have already tried the following:
- New installation of RM 9.7
- RM 9.8 BETA (same problem)
- Repository location changed
My system:
- Win 10 X64
- RM Studio 9.7 (latest)
- all admin privileges
Unfortunately nothing leads to success. I have attached my process to store the data here, maybe you can help me. As mentioned the code to store works. I can't retrieve the .rmhdf5table-file (also attached).
Kind regards,
Patrick
<?xml version="1.0" encoding="UTF-8"?><process version="9.7.002">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="9.7.002" expanded="true" name="Process">
<parameter key="logverbosity" value="init"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="never"/>
<parameter key="notification_email" value=""/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<process expanded="true">
<operator activated="true" class="read_csv" compatibility="9.7.002" expanded="true" height="68" name="Read CSV" width="90" x="45" y="85">
<parameter key="csv_file" value="C:/Users/patri/Dropbox/Team Asia/asia.csv"/>
<parameter key="column_separators" value=";"/>
<parameter key="trim_lines" value="false"/>
<parameter key="use_quotes" value="true"/>
<parameter key="quotes_character" value="""/>
<parameter key="escape_character" value="\"/>
<parameter key="skip_comments" value="false"/>
<parameter key="comment_characters" value="#"/>
<parameter key="starting_row" value="1"/>
<parameter key="parse_numbers" value="true"/>
<parameter key="decimal_character" value="."/>
<parameter key="grouped_digits" value="false"/>
<parameter key="grouping_character" value=","/>
<parameter key="infinity_representation" value=""/>
<parameter key="date_format" value=""/>
<parameter key="first_row_as_names" value="true"/>
<list key="annotations"/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<parameter key="encoding" value="UTF-8"/>
<parameter key="read_all_values_as_polynominal" value="false"/>
<list key="data_set_meta_data_information"/>
<parameter key="read_not_matching_values_as_missings" value="true"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<operator activated="true" class="filter_example_range" compatibility="9.7.002" expanded="true" height="82" name="Filter Example Range" width="90" x="179" y="85">
<parameter key="first_example" value="1"/>
<parameter key="last_example" value="1"/>
<parameter key="invert_filter" value="false"/>
</operator>
<operator activated="true" class="web:retrieve_webpages" compatibility="9.3.001" expanded="true" height="68" name="Get Pages" width="90" x="313" y="85">
<parameter key="link_attribute" value="roughguide link"/>
<parameter key="page_attribute" value="content"/>
<parameter key="random_user_agent" value="false"/>
<parameter key="connection_timeout" value="10000"/>
<parameter key="read_timeout" value="10000"/>
<parameter key="follow_redirects" value="false"/>
<parameter key="accept_cookies" value="none"/>
<parameter key="cookie_scope" value="global"/>
<parameter key="request_method" value="GET"/>
<parameter key="delay" value="none"/>
<parameter key="delay_amount" value="1000"/>
<parameter key="min_delay_amount" value="0"/>
<parameter key="max_delay_amount" value="1000"/>
</operator>
<operator activated="true" class="select_attributes" compatibility="9.7.002" expanded="true" height="82" name="Select Attributes" width="90" x="447" y="85">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attribute" value="content"/>
<parameter key="attributes" value="content|continent|place|country|roughguide link"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
</operator>
<operator activated="true" class="set_role" compatibility="9.7.002" expanded="true" height="82" name="Set Role" width="90" x="581" y="85">
<parameter key="attribute_name" value="roughguide link"/>
<parameter key="target_role" value="id"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="store" compatibility="9.7.002" expanded="true" height="68" name="Store" width="90" x="715" y="85">
<parameter key="repository_entry" value="../data/raw_extract_asia"/>
</operator>
<connect from_op="Read CSV" from_port="output" to_op="Filter Example Range" to_port="example set input"/>
<connect from_op="Filter Example Range" from_port="example set output" to_op="Get Pages" to_port="Example Set"/>
<connect from_op="Get Pages" from_port="Example Set" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Store" to_port="input"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
</process>
</operator>
</process>
