Index

A

aux_list (publicbr.caged._crawler.CagedCrawler attribute) aux_paths (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute)

AuxCleaner (class in publicbr.cnpj._consolidation) available_aux (publicbr.caged._crawler.CagedCrawler attribute)

B

base_url (publicbr.cnpj._crawler.CNPJCrawler attribute)

C

caged_levels (publicbr.caged._consolidation.CagedCleaner attribute) CagedCleaner (class in publicbr.caged._consolidation) CagedCrawler (class in publicbr.caged._crawler) CagedSource (class in publicbr.caged._source) callback_save() (publicbr.caged._crawler.CagedCrawler method) change_ftp_dir() (publicbr.caged._crawler.CagedCrawler method) clean() (publicbr.caged._consolidation.CagedCleaner method) (publicbr.cnpj._consolidation.AuxCleaner method) (publicbr.cnpj._consolidation.EmpresasCleaner method) (publicbr.cnpj._consolidation.EstabCleaner method) (publicbr.cnpj._consolidation.SimplesCleaner method) (publicbr.cnpj._consolidation.SociosCleaner method)

cleaner (publicbr.caged._source.CagedSource attribute) cleaners (publicbr.cnpj._source.CNPJSource attribute) CNPJCrawler (class in publicbr.cnpj._crawler) CNPJSource (class in publicbr.cnpj._source) crawler (publicbr.cnpj._source.CNPJSource attribute) create() (publicbr.caged._source.CagedSource method) (publicbr.cnpj._source.CNPJSource method) create_connection() (publicbr.caged._crawler.CagedCrawler method)

D

define_schema() (publicbr.caged._consolidation.CagedCleaner method) (publicbr.cnpj._consolidation.AuxCleaner method) (publicbr.cnpj._consolidation.EmpresasCleaner method) (publicbr.cnpj._consolidation.EstabCleaner method) (publicbr.cnpj._consolidation.SimplesCleaner method) (publicbr.cnpj._consolidation.SociosCleaner method) df (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SimplesCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute)

df_cleaned (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SimplesCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute) download_url() (publicbr.cnpj._crawler.CNPJCrawler method)

E

EmpresasCleaner (class in publicbr.cnpj._consolidation) EstabCleaner (class in publicbr.cnpj._consolidation)

extract() (publicbr.caged._source.CagedSource method) (publicbr.cnpj._source.CNPJSource method)

F

file_dir (publicbr.caged._consolidation.CagedCleaner attribute) (publicbr.cnpj._consolidation.AuxCleaner attribute) (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SimplesCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute) file_ids (publicbr.cnpj._consolidation.AuxCleaner attribute)

file_name (publicbr.caged._consolidation.CagedCleaner attribute) file_path (publicbr.cnpj._consolidation.SimplesCleaner attribute) files (publicbr.cnpj._consolidation.AuxCleaner attribute) (publicbr.cnpj._crawler.CNPJCrawler attribute) ftp (publicbr.caged._crawler.CagedCrawler attribute) ftp_folders (publicbr.caged._crawler.CagedCrawler attribute) (publicbr.caged._source.CagedSource attribute)

G

get_data() (publicbr.caged._crawler.CagedCrawler method) (publicbr.cnpj._crawler.CNPJCrawler method) get_download_files() (publicbr.caged._crawler.CagedCrawler method)

get_file_info() (publicbr.caged._crawler.CagedCrawler method) get_files() (publicbr.cnpj._consolidation.AuxCleaner method) get_layout_file() (publicbr.caged._crawler.CagedCrawler method) get_most_recent_file() (publicbr.caged._crawler.CagedCrawler method)

H

host (publicbr.caged._crawler.CagedCrawler attribute)

I

int_dir (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute)

int_path (publicbr.cnpj._consolidation.SociosCleaner attribute)

J

join_aux_tables() (publicbr.caged._consolidation.CagedCleaner method)

L

layout_file (publicbr.caged._crawler.CagedCrawler attribute)

M

module publicbr.caged._consolidation publicbr.caged._crawler publicbr.caged._source publicbr.cnpj._consolidation publicbr.cnpj._crawler publicbr.cnpj._source

P

publicbr.caged._consolidation module publicbr.caged._crawler module publicbr.caged._source module

publicbr.cnpj._consolidation module publicbr.cnpj._crawler module publicbr.cnpj._source module

R

raw_dir (publicbr.caged._source.CagedSource attribute) (publicbr.cnpj._source.CNPJSource attribute)

run() (publicbr.caged._crawler.CagedCrawler method) (publicbr.cnpj._crawler.CNPJCrawler method)

S

save_aux_tables() (publicbr.caged._crawler.CagedCrawler method) save_dir (publicbr.caged._consolidation.CagedCleaner attribute) (publicbr.caged._crawler.CagedCrawler attribute) (publicbr.cnpj._consolidation.AuxCleaner attribute) (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SimplesCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute) (publicbr.cnpj._crawler.CNPJCrawler attribute) save_path (publicbr.cnpj._consolidation.SimplesCleaner attribute) schema (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SimplesCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute)

SimplesCleaner (class in publicbr.cnpj._consolidation) SociosCleaner (class in publicbr.cnpj._consolidation) spark (publicbr.caged._consolidation.CagedCleaner attribute) (publicbr.caged._source.CagedSource attribute) (publicbr.cnpj._consolidation.AuxCleaner attribute) (publicbr.cnpj._consolidation.EmpresasCleaner attribute) (publicbr.cnpj._consolidation.EstabCleaner attribute) (publicbr.cnpj._consolidation.SimplesCleaner attribute) (publicbr.cnpj._consolidation.SociosCleaner attribute) (publicbr.cnpj._source.CNPJSource attribute)

T

transform() (publicbr.caged._source.CagedSource method) (publicbr.cnpj._source.CNPJSource method) transform_data() (publicbr.caged._consolidation.CagedCleaner method) (publicbr.cnpj._consolidation.AuxCleaner method) (publicbr.cnpj._consolidation.EmpresasCleaner method) (publicbr.cnpj._consolidation.EstabCleaner method) (publicbr.cnpj._consolidation.SimplesCleaner method) (publicbr.cnpj._consolidation.SociosCleaner method)

trusted_dir (publicbr.caged._source.CagedSource attribute) (publicbr.cnpj._source.CNPJSource attribute)

U

unzip() (publicbr.cnpj._crawler.CNPJCrawler method)

unzip_files() (publicbr.caged._crawler.CagedCrawler method)