python转换xsl到csv与整理json

Posted

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了python转换xsl到csv与整理json相关的知识,希望对你有一定的参考价值。


# -*- coding: utf-8 -*-

Find the time and value of max load for each of the regions
COAST, EAST, FAR_WEST, NORTH, NORTH_C, SOUTHERN, SOUTH_C, WEST
and write the result out in a csv file, using pipe character | as the delimiter.

An example output can be seen in the "example.csv" file.

import xlrd
import os
import csv
from zipfile import ZipFile

datafile = "2013_ERCOT_Hourly_Load_Data.xls"
outfile = "2013_Max_Loads.csv"

def open_zip(datafile):
    with ZipFile(0.zip.format(datafile), r) as myzip:
        myzip.extractall()

def parse_file(datafile):
    workbook = xlrd.open_workbook(datafile)
    sheet = workbook.sheet_by_index(0)
    data =
    # process all rows that contain station data
    for n in range (1, 9):
        station = sheet.cell_value(0, n)
        cv = sheet.col_values(n, start_rowx=1, end_rowx=None)

        maxval = max(cv)
        maxpos = cv.index(maxval) + 1
        maxtime = sheet.cell_value(maxpos, 0)
        realtime = xlrd.xldate_as_tuple(maxtime, 0)
        data[station] = "maxval": maxval,
                         "maxtime": realtime

    print data
    return data

def save_file(data, filename):
    with open(filename, "w") as f:
        w = csv.writer(f, delimiter=|)
        w.writerow(["Station", "Year", "Month", "Day", "Hour", "Max Load"])
        for s in data:
            year, month, day, hour, _ , _= data[s]["maxtime"]
            w.writerow([s, year, month, day, hour, data[s]["maxval"]])

    
def test():
    open_zip(datafile)
    data = parse_file(datafile)
    save_file(data, outfile)

    number_of_rows = 0
    stations = []

    ans = FAR_WEST: Max Load: 2281.2722140000024,
                        Year: 2013,
                        Month: 6,
                        Day: 26,
                        Hour: 17
    correct_stations = [COAST, EAST, FAR_WEST, NORTH,
                        NORTH_C, SOUTHERN, SOUTH_C, WEST]
    fields = [Year, Month, Day, Hour, Max Load]

    with open(outfile) as of:
        csvfile = csv.DictReader(of, delimiter="|")
        for line in csvfile:
            station = line[Station]
            if station == FAR_WEST:
                for field in fields:
                    # Check if Max Load is within .1 of answer
                    if field == Max Load:
                        max_answer = round(float(ans[station][field]), 1)
                        max_line = round(float(line[field]), 1)
                        assert max_answer == max_line

                    # Otherwise check for equality
                    else:
                        assert ans[station][field] == line[field]

            number_of_rows += 1
            stations.append(station)

        # Output should be 8 lines not including header
        assert number_of_rows == 8

        # Check Station Names
        assert set(stations) == set(correct_stations)

        
if __name__ == "__main__":
    test()
 

 

 

 

 

###########

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
This exercise shows some important concepts that you should be aware about:
- using codecs module to write unicode files
- using authentication with web APIs
- using offset when accessing web APIs

To run this code locally you have to register at the NYTimes developer site 
and get your own API key. You will be able to complete this exercise in our UI
without doing so, as we have provided a sample result. (See the file 
popular-viewed-1.json from the tabs above.)

Your task is to modify the article_overview() function to process the saved
file that represents the most popular articles (by view count) from the last
day, and return a tuple of variables containing the following data:
- labels: list of dictionaries, where the keys are the "section" values and
  values are the "title" values for each of the retrieved articles.
- urls: list of URLs for all media entries with "format": "Standard Thumbnail"

All your changes should be in the article_overview() function. See the test() 
function for examples of the elements of the output lists.
The rest of functions are provided for your convenience, if you want to access
the API by yourself.
"""
import json
import codecs
import requests

URL_MAIN = "http://api.nytimes.com/svc/"
URL_POPULAR = URL_MAIN + "mostpopular/v2/"
API_KEY = "popular": "",
            "article": ""

def get_from_file(kind, period):
    filename = "popular-0-1.json".format(kind, period)
    with open(filename, "r") as f:
        return json.loads(f.read())

def article_overview(kind, period):
    data = get_from_file(kind, period)
    titles = []
    urls =[]

    for article in data:
        section = article["section"]
        title = article["title"]
        titles.append(section: title)
        if "media" in article:
            for m in article["media"]:
                for mm in m["media-metadata"]:
                    if mm["format"] == "Standard Thumbnail":
                        urls.append(mm["url"])
    return (titles, urls)

def query_site(url, target, offset):
    # This will set up the query with the API key and offset
    # Web services often use offset paramter to return data in small chunks
    # NYTimes returns 20 articles per request, if you want the next 20
    # You have to provide the offset parameter
    if API_KEY["popular"] == "" or API_KEY["article"] == "":
        print "You need to register for NYTimes Developer account to run this program."
        print "See Intructor notes for information"
        return False
    params = "api-key": API_KEY[target], "offset": offset
    r = requests.get(url, params = params)

    if r.status_code == requests.codes.ok:
        return r.json()
    else:
        r.raise_for_status()

def get_popular(url, kind, days, section="all-sections", offset=0):
    # This function will construct the query according to the requirements of the site
    # and return the data, or print an error message if called incorrectly
    if days not in [1,7,30]:
        print "Time period can be 1,7, 30 days only"
        return False
    if kind not in ["viewed", "shared", "emailed"]:
        print "kind can be only one of viewed/shared/emailed"
        return False

    url += "most0/1/2.json".format(kind, section, days)
    data = query_site(url, "popular", offset)

    return data

def save_file(kind, period):
    # This will process all results, by calling the API repeatedly with supplied offset value,
    # combine the data and then write all results in a file.
    data = get_popular(URL_POPULAR, "viewed", 1)
    num_results = data["num_results"]
    full_data = []
    with codecs.open("popular-0-1.json".format(kind, period), encoding=utf-8, mode=w) as v:
        for offset in range(0, num_results, 20):        
            data = get_popular(URL_POPULAR, kind, period, offset=offset)
            full_data += data["results"]
        
        v.write(json.dumps(full_data, indent=2))

def test():
    titles, urls = article_overview("viewed", 1)
    assert len(titles) == 20
    assert len(urls) == 30
    assert titles[2] == Opinion: Professors, We Need You!
    assert urls[20] == http://graphics8.nytimes.com/images/2014/02/17/sports/ICEDANCE/ICEDANCE-thumbStandard.jpg

if __name__ == "__main__":
    test()

以上是关于python转换xsl到csv与整理json的主要内容,如果未能解决你的问题,请参考以下文章

如何使用 XSL 将 XML 转换为 CSV

Python爬虫编程思想(157):使用Scrapy从CSV格式转换到JSON格式

Python爬虫编程思想(157):使用Scrapy从CSV格式转换到JSON格式

Python爬虫编程思想(157):使用Scrapy从CSV格式转换到JSON格式

如何使用 XSL 将 liquibase XML 转换为 CSV

XSLT 1.0:CSV 到 XML - 如何分而治之