Question

我有一个程序，最后打印出一个“匹配”我想将这个“匹配”中的数据保存到csv文件中，我该怎么做？我写了一些代码来保存这个变量，但它没有写任何东西这是我的代码：

import shlex
import subprocess
import os
import platform
from bs4 import BeautifulSoup
import re
import csv
import pickle
def rename_files():
    file_list = os.listdir(r"C:\\PROJECT\\pdfs")
    print(file_list)
    saved_path = os.getcwd()
    print('Current working directory is '+saved_path)
    os.chdir(r'C:\\PROJECT\\pdfs')
    for file_name in file_list:
        os.rename(file_name, file_name.translate(None, " "))
    os.chdir(saved_path)
rename_files()

def run(command):
    if platform.system() != 'Windows':
        args = shlex.split(command)
    else:
        args = command
    s = subprocess.Popen(args,
                         stdout=subprocess.PIPE,
                         stderr=subprocess.PIPE)
    output, errors = s.communicate()
    return s.returncode == 0, output, errors

# Change this to your PDF file base directory
base_directory = 'C:\\PROJECT\\pdfs'
if not os.path.isdir(base_directory):
    print "%s is not a directory" % base_directory
    exit(1)
# Change this to your pdf2htmlEX executable location
bin_path = 'C:\\Python27\\pdfminer-20140328\\tools\\pdf2txt.py'
if not os.path.isfile(bin_path):
    print "Could not find %s" % bin_path
    exit(1)
for dir_path, dir_name_list, file_name_list in os.walk(base_directory):
    for file_name in file_name_list:
        # If this is not a PDF file
        if not file_name.endswith('.pdf'):
            # Skip it
            continue
        file_path = os.path.join(dir_path, file_name)
        # Convert your PDF to HTML here
        args = (bin_path, file_name, file_path)
        success, output, errors = run("python %s -o %s.html %s " %args)
        if not success:
            print "Could not convert %s to HTML" % file_path
            print "%s" % errors
htmls_path = 'C:\\PROJECT'
for dir_path, dir_name_list, file_name_list in os.walk(htmls_path):
    for file_name in file_name_list:
        if not file_name.endswith('.html'):
            continue
        with open(file_name) as markup:
            soup = BeautifulSoup(markup.read())
            text = soup.get_text()
            match = re.findall("PA/(\S*)\s*(\S*)", text)
            print(match)
with open ('score.csv', 'w') as f:
    writer = csv.writer(f)
    writer.writerows('%s' %match)

我尝试将其保存到csv文件中的部分是最后3行代码。以下是“匹配”格式的打印件：https://gyazo.com/930f9dad12109bc50825c91b51fb31f3

Answer 1

假设您已经拥有“匹配”，则可以在Python中使用CSV module。作者应该完成你的工作。

如果您能详细说明数据的格式，那会更有帮助。

Answer 2

您的代码的结构方式，您在for循环中迭代匹配，然后，当循环结束时，您保存CSV中的最后一个匹配。您可能希望在for循环内写入CSV中的每个匹配项。

尝试通过以下方式替换代码的最后几行（从最后for循环开始）：

with open('score.csv', 'wt') as f:
    writer = csv.writer(f)
    for dir_path, dir_name_list, file_name_list in os.walk(htmls_path):
        for file_name in file_name_list:
            if not file_name.endswith('.html'):
                continue
            with open(file_name) as markup:
                soup = BeautifulSoup(markup.read())
                text = soup.get_text()
                match = re.findall("PA/(\S*)\s*(\S*)", text)
                print(match)
                writer.writerow(match)

如何将数据从python保存到csv文件中

2 个答案: