Python利用Rows快速操作csv文件

pip install rows

state,city,inhabitants,area
AC,Acrelândia,12538,1807.92
AC,Assis Brasil,6072,4974.18
AC,Brasiléia,21398,3916.5
AC,Bujari,8471,3034.87
AC,Capixaba,8798,1702.58
[...]
RJ,Angra dos Reis,169511,825.09
RJ,Aperibé,10213,94.64
RJ,Araruama,112008,638.02
RJ,Areal,11423,110.92
RJ,Armação dos BúziOS,27560,70.28
[...]

import rows
 
cities = rows.import_from_csv("data/brazilian-cities.csv")
rio_biggest_cities = [
    city for city in cities
    if city.state == "RJ" and city.inhabitants > 500000
]
for city in rio_biggest_cities:
    density = city.inhabitants / city.area
    print(f"{city.city} ({density:5.2f} ppl/km²)")

from collections import OrderedDict
from rows import fields, Table
 
 
country_fields = OrderedDict([
    ("name", fields.TextField),
    ("population", fields.IntegerField),
])
 
countries = Table(fields=country_fields)
countries.append({"name": "Argentina", "population": "45101781"})
countries.append({"name": "Brazil", "population": "212392717"})
countries.append({"name": "Colombia", "population": "49849818"})
countries.append({"name": "Ecuador", "population": "17100444"})
countries.append({"name": "Peru", "population": "32933835"})

for country in countries:
    print(country)
# Result:
# Row(name='Argentina', population=45101781)
# Row(name='Brazil', population=212392717)
# Row(name='Colombia', population=49849818)
# Row(name='Ecuador', population=17100444)
# Row(name='Peru', population=32933835)
# "Row" is a namedtuple created from `country_fields`
 
# We've added population as a string, the library automatically converted to
# integer so we can also sum:
countries_population = sum(country.population for country in countries)
print(countries_population) # prints 357378595

# 公众号：Python实用宝典
import rows
rows.export_to_csv(countries, "some-LA-countries.csv")
 
# html
rows.export_to_html(leGISlators, "some-LA-countries.csv")

import rows
 
data = [
    {"name": "Argentina", "population": "45101781"},
    {"name": "Brazil", "population": "212392717"},
    {"name": "Colombia", "population": "49849818"},
    {"name": "Ecuador", "population": "17100444"},
    {"name": "Peru", "population": "32933835"},
    {"name": "Guyana", }, # Missing "population", will fill with `None`
]
table = rows.import_from_dicts(data)
print(table[-1]) # Can use indexes
# Result:
# Row(name='Guyana', population=None)

# 需要提前安装: pip install rows[pdf]
URL="Http://www.imprensaoficial.rr.Gov.br/app/_edicoes/2018/01/doe-20180131.pdf"
rows pdf-to-text $URL result.txt # 保存到文件 显示进度条
rows pdf-to-text --quiet $URL result.txt # 保存到文件 不显示进度条
rows pdf-to-text --pages=1,2,3 $URL # 输出三页到终端
rows pdf-to-text --pages=1-3 $URL # 输出三页到终端(使用 - 范围符)

rows csv2sqlite \
     --dialect=excel \
     --input-encoding=latin1 \
     file1.csv file2.csv \
     result.sqlite

rows csv-merge \
     file1.csv file2.csv.bz2 file3.csv.xz \
     result.csv.gz

# needs: pip install rows[html]
rows query \
    "SELECT * FROM table1 WHERE inhabitants > 1000000" \
    data/brazilian-cities.csv \
    --output=data/result.html