Question

我的代码工作正常，但是我不确定为什么当我尝试输出到csv时。当我使用“打印”时，行数是两倍。

我似乎无法解释多余的行是从哪里来的。

这是我保存到csv时的代码

url1 = 'https://yugioh.fandom.com/wiki/Set_Card_Lists:Deck_Build_Pack:_Mystic_Fighters_(OCG-JP)'
output_file1_2 = "DBMF - CardList - tr2.csv" #change this to your own file output

def OutputHTMLFileSummary2(url,html_tag,output_file):
    array = []
    source = urllib.request.urlopen(url).read()
    soup = bs.BeautifulSoup(source, 'html.parser')
    f = csv.writer(open(output_file, "w", encoding="utf-8"))
    links = soup.find_all(html_tag)

    counter = 0.0
    for link in links:
        counter += 1
        if (counter/2) != 0.0:
            array.append([f.text.strip().replace("\xa0\n\t", "") for f in link.find_all("td")])
            print(counter)
        else:
            pass
    print(array)
    for i in range(len(array)):
        f.writerow([array[i]])
OutputHTMLFileSummary2(url1,"tr",output_file6)

file = open(output_file6, encoding="utf-8")
reader = csv.reader(file)
lines= len(list(reader))
print(lines)

The output in csv

Answer 1

似乎可以为我工作。我对打印输出进行了一些调整，但它们的大小相同。

import bs4 as bs
import urllib
import csv

url1 = 'https://yugioh.fandom.com/wiki/Set_Card_Lists:Deck_Build_Pack:_Mystic_Fighters_(OCG-JP)'
output_file = "DBMF - CardList - tr2.csv" #change this to your own file output

def OutputHTMLFileSummary2(url,html_tag,output_file):
    array = []
    source = urllib.request.urlopen(url).read()
    soup = bs.BeautifulSoup(source, 'html.parser')
    with open(output_file, "w", encoding="utf-8") as src:
        f = csv.writer(src)
        links = soup.find_all(html_tag)

        counter = 0.0
        for link in links:
            counter += 1
            if (counter/2) != 0.0:   # <---- do NOT do this...
                array.append([f.text.strip().replace("\xa0\n\t", "") for f in link.find_all("td")])
                print(counter)
            else:
                pass
        for idx, item in enumerate(array):
            print(f'{idx}: {item}')
        #print(array)
        for i in range(len(array)):
            f.writerow([array[i]])

OutputHTMLFileSummary2(url1,"tr",output_file)

file = open(output_file, encoding="utf-8")
reader = csv.reader(file)
#lines= len(list(reader))
print('\nFrom the file...\n')
for idx, item in enumerate(reader):
    print(f'{idx}: {item}')
file.close()

从HTML页面抓取后的CSV问题

1 个答案: