将数组数据放在 csv 文件中

Question

如何将数组输出保存为 csv 文件？ 我试过使用 csv 模块，但没有给我正确的输出。我想要如下图所示的输出。

output1.html

<div class="side-article txt-article">
    <p><strong></strong> <a href="http://batam.tribunnews.com/tag/polres/" title="Polres"></a> <a href="http://batam.tribunnews.com/tag/bintan/" title="Bintan"></a></p>
    <p><br></p>
    <p><a href="http://batam.tribunnews.com/tag/polres/" title="Polres"></a></p>
    <p><a href="http://batam.tribunnews.com/tag" title="Polres"></a> <a href="http://batam.tribunnews.com/tag/bintan/" title="Bintan"></a></p>
    <br>

我有代码：

import csv
from bs4 import BeautifulSoup
from HTMLParser import HTMLParser

with open('output1.html', 'r') as f:
    html = f.read()
soup = BeautifulSoup(html.strip(), 'html.parser')

for line in html.strip().split('\n'):
    link_words = 0

    line_soup = BeautifulSoup(line.strip(), 'html.parser')
    for link in line_soup.findAll('a'):
        link_words += len(link.text.split())

    # naive way to get words count
    words_count = len(line_soup.text.split())- link_words

    number_tag_p = len(line_soup.find_all('p'))
    number_tag_br = len(line_soup.find_all('br'))
    number_tag_break = number_tag_br + number_tag_p

    #for line in html.strip().split('\n'):
    number_of_starttags = 0
    number_of_endtags = 0


        # create a subclass and override the handler methods
    class MyHTMLParser(HTMLParser):
        def handle_starttag(self, tag, attrs):
            global number_of_starttags
            number_of_starttags += 1

        def handle_endtag(self, tag):
            global number_of_endtags
            number_of_endtags += 1

                # instantiate the parser and fed it some HTML


    parser = MyHTMLParser()
    parser.feed(line.lstrip())
    number_tag = number_of_starttags + number_of_endtags
    #print(number_of_starttags + number_of_endtags)
    CTTD = words_count + link_words + number_tag_break


    if (words_count + link_words) == 0:
        CTTD == 0
    else:
        CTTD

    print ('TC : {0} LTC : {1} TG : {2} P : {3} CTTD : {4}'
           .format(words_count, link_words, number_tag, number_tag_break, CTTD))



res = ('TC : {0} LTC : {1} TG : {2} P : {3} CTTD : {4}'
           .format(words_count, link_words, number_tag, number_tag_break, CTTD))
csvfile = "./output1.csv"

#Assuming res is a flat list
with open(csvfile, "wb") as output:
    writer = csv.writer(output, lineterminator='\n')
    for val in res:
        writer.writerow([val])

#Assuming res is a list of lists
with open(csvfile, "wb") as output:
    writer = csv.writer(output, lineterminator='\n')
    writer.writerows(res)

算法的输出

TC : 0 LTC : 0 TG : 0 P : 0 CTTD : 0
TC : 0 LTC : 0 TG : 0 P : 0 CTTD : 0
TC : 0 LTC : 0 TG : 1 P : 0 CTTD : 0
TC : 0 LTC : 0 TG : 1 P : 0 CTTD : 0
TC : 15 LTC : 0 TG : 2 P : 0 CTTD : 15

输出 csv：

如何将打印保存到 csv？ 任何python库都可以做到这一点？

我预计输出将是

谢谢。

Answer 1

也许这就是你想要的：

import csv
from bs4 import BeautifulSoup
from html.parser import HTMLParser

class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        global number_of_starttags
        number_of_starttags += 1

    def handle_endtag(self, tag):
        global number_of_endtags
        number_of_endtags += 1

with open('output1.html', 'r') as f:
    html = f.read()
soup = BeautifulSoup(html.strip(), 'html.parser')

ress = []
for line in html.strip().split('\n'):
    link_words = 0

    line_soup = BeautifulSoup(line.strip(), 'html.parser')
    for link in line_soup.findAll('a'):
        link_words += len(link.text.split())

    words_count = len(line_soup.text.split())- link_words
    number_tag_p = len(line_soup.find_all('p'))
    number_tag_br = len(line_soup.find_all('br'))
    number_tag_break = number_tag_br + number_tag_p

    number_of_starttags = 0
    number_of_endtags = 0

    parser = MyHTMLParser()
    parser.feed(line.lstrip())
    number_tag = number_of_starttags + number_of_endtags
    CTTD = words_count + link_words + number_tag_break


    if (words_count + link_words) == 0:
        CTTD == 0
    res = [words_count, link_words, number_tag, number_tag_break, CTTD]
    ress.append(res)

csvfile = "./output.csv"
firstline = ["TC", "LTC", "TG", "P", "CTTD"]
with open(csvfile, "w") as output:
    writer = csv.writer(output, lineterminator='\n')
    writer.writerow(firstline)
    for val in ress:
        writer.writerow(val)

无论如何，我的输出与你的不同......我得到了这个 csv：

TC,LTC,TG,P,CTTD
0,0,1,0,0
0,0,8,1,1
0,0,3,2,2
0,0,4,1,1
0,0,6,1,1
0,0,1,1,1

因为你在 for cicle 中只有最后一行值（你的 . 格式在 for 范围之外）

Answer 2

writerow 获取元素列表，这些元素构成特定行中单元格的值。

因此，在写入 csv 时，始终建议将标题构建为列表，并将所有值构建为列表列表

header = ["TC", "LTC", "TG", "P", "CTTD"]
val = [[1,2,3,4],[2,3,4,5]]
with open(csvfile, "w") as output:
    writer = csv.writer(output, lineterminator='\n')
    writer.writerow(header)
    for v in val:
        writer.writerow(v)