如何使用 python 将多列写入 CSV header？

Question

我目前正在使用 python 2.7 在网站的源代码中抓取多个关键字。我想将这些关键字分配并导出到导出的 CSV 文件中的各个列，如下所示：

但是，通过我的代码，我得到了这个：

我的代码：

import urllib2
import csv

fieldnames = ['Website', 'Sitemap', 'Viewport', '@media']

def csv_writerheader(path):
    with open(path, 'w') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        writer.writeheader()

def csv_writer(domainname,Sitemap, path):
    with open(path, 'a') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        # writer.writeheader()
        writer.writerow({'Website': domainname, 'Sitemap': Sitemap})

csv_output_file = 'exported_print_results.csv'
keyword1 = ['sitemap']
keyword2 = ['viewport']
keyword3 = ['@media']

csv_writerheader(csv_output_file)

f = open('top1m-edited.csv')
csv_f = csv.reader(f)
for line in f:
    strdomain = line.strip()
    if '.nl' in strdomain:
        try:
            req = urllib2.Request(strdomain.strip())
            response = urllib2.urlopen(req)
            html_content = response.read()

            # keyword 1
            for searchstring in keyword1:
                if searchstring.lower() in str(html_content).lower():
                    print (strdomain, keyword1, 'found')
                    csv_writer(strdomain, 'found', csv_output_file)

                else:
                    print (strdomain, keyword1, 'not found')
                    csv_writer(strdomain, 'not found', csv_output_file)

            # keyword 2
            for searchstring in keyword2:
                if searchstring.lower() in str(html_content).lower():
                    print (strdomain, keyword2, 'found')
                    csv_writer(strdomain, 'found', csv_output_file)

                else:
                    print (strdomain, keyword2, 'not found')
                    csv_writer(strdomain, 'not found', csv_output_file)

            # keyword 3
            for searchstring in keyword3:
                if searchstring.lower() in str(html_content).lower():
                    print (strdomain, keyword3, 'found')
                    csv_writer(strdomain, 'found', csv_output_file)

                else:
                    print (strdomain, keyword3, 'not found')
                    csv_writer(strdomain, 'not found', csv_output_file)

        except urllib2.HTTPError:
            print (strdomain, 'HTTP ERROR')

        except urllib2.URLError:
            print (strdomain, 'URL ERROR')

        except urllib2.socket.error:
            print (strdomain, 'SOCKET ERROR')

        except urllib2.ssl.CertificateError:
            print (strdomain, 'SSL Certificate ERROR')
f.close()

我应该如何编辑我的代码才能使其正常工作？

Answer 1

电子表格中的默认分隔符似乎不是逗号。它很可能是一个 TAB。您可以在导入时将分隔符更改为逗号（通常有一个导入对话框允许您 select 它）或从 Python 输出并使用 TAB 作为字段分隔符。

Answer 2

考虑使用字典按关键字有条件地存储 found 和 not found 值，并将其传递到您的 csv 写入方法中。但在此之前，您的一个问题是没有在 csv.writer() 中指定 lineterminator，而 Window 文本文件往往需要它。并尝试在一个循环例程中遍历关键字列表。

fieldnames = ['Website', 'Sitemap', 'Viewport', '@media']

def csv_writerheader(path):
    with open(path, 'w') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames, lineterminator='\n')
        writer.writeheader()

def csv_writer(dictdata, path):
    with open(path, 'a') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames, lineterminator='\n')
        writer.writerow(dictdata)

csv_output_file = 'exported_print_results.csv'
# LIST OF KEY WORDS (TITLE CASE TO MATCH FIELD NAMES)
keywords = ['Sitemap', 'Viewport', '@media']

csv_writerheader(csv_output_file)

with open('top1m-edited.csv', 'r') as f:
    csv_f = csv.reader(f, lineterminator='\n')
    for line in f:
        strdomain = line.strip()
        # INITIALIZE DICT
        data = {'Website': strdomain}

        if '.nl' in strdomain:        
            try:
                req = urllib2.Request(strdomain.strip())
                response = urllib2.urlopen(req)
                html_content = response.read()

                # ITERATE THROUGH EACH KEY AND UPDATE DICT
                for searchstring in keywords:
                    if searchstring.lower() in str(html_content).lower():
                        print (strdomain, searchstring, 'found')
                        data[searchstring] = 'found'    
                    else:
                        print (strdomain, searchstring, 'not found')
                        data[searchstring] = 'not found'

                # CALL METHOD PASSING DICT AND OUTPUT FILE
                csv_writer(data, csv_output_file)

                except urllib.HTTPError:
                    print (strdomain, 'HTTP ERROR')

                except urllib.URLError:
                    print (strdomain, 'URL ERROR')

                except urllib.socket.error:
                    print (strdomain, 'SOCKET ERROR')

                except urllib.ssl.CertificateError:
                    print (strdomain, 'SSL Certificate ERROR')

CSV 输出

Website                 Sitemap     Viewport    @media
http://www.google.nl    not found   not found   found
http://www.youtube.nl   not found   found       not found
http://www.facebook.nl  not found   found       not found

如何使用 python 将多列写入 CSV header？

How to write multiple columns to a CSV header using python?

python

csv

export-to-csv