Question

我有一个程序使用RoboBrowser向网站发送大量请求并获得答案，但现在我需要将这些答案过滤到那些没有这个字符串的答案＆＃ 34;案件状态不可用＆＃34;我尝试使用beautifulsoup，但它返回错误。

到目前为止，这是代码：

import shlex
import subprocess
import os
import platform
from bs4 import BeautifulSoup
import re
import csv
import pickle
import requests
from robobrowser import RoboBrowser

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'
with open ('score.csv', 'w') 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*)", text)#To remove the names that appear, just remove the last (\S*), to add them is just add the (\S*), before it there was a \s*
                print(match)
                writer.writerow(match)
                for item in match:
                    data = item.split('/')
                    case_number = data[0]
                    case_year = data[1]

                    browser = RoboBrowser()
                    browser.open('http://www.pa.org.mt/page.aspx?n=63C70E73&CaseType=PA')
                    form = browser.get_forms()[0]  # Get the first form on the page
                    form['ctl00$PageContent$ContentControl$ctl00$txtCaseNo'].value = case_number
                    form['ctl00$PageContent$ContentControl$ctl00$txtCaseYear'].value = case_year

                    browser.submit_form(form, submit=form['ctl00$PageContent$ContentControl$ctl00$btnSubmit'])

                    # Use BeautifulSoup to parse this data
                    print(browser.response.text)
                    souptwo = BeautifulSoup(browser.response.text)
                    texttwo = soup.get_text()
                    matchtwo = soup.findall('<td class="fieldData">Case Status Not Available</TD>')
                    if not matchtwo:
                        soupthree = BeautifulSoup(browser.response.text)
                        print soupthree

返回的错误是：

Traceback (most recent call last):
  File "C:\PROJECT\pdfs\converterpluspa.py", line 87, in <module>
    matchtwo = soup.findall('<td class="fieldData">Case Status Not Available</TD>')
TypeError: 'NoneType' object is not callable

Answer 1

第87行包含尝试调用findall的方法soup。第65行定义了soup，其中调用了BeautifulSoup来解析文件的内容。由于错误诊断显示soup为None，这意味着BeautifulSoup无法解析该文件。

如何扼杀浏览器响应

1 个答案: