Abram's questions

为什么python代码中无法读取并打印word文件的内容：

import bs4
import time
import random
import requests
import docx
from bs4 import BeautifulSoup
from requests_html import HTMLSession
import magic
import chardet
import codecs
from io import BytesIO
from docx import Document

from selenium import webdriver  # pip install selenium


# Список пользовательских агентов
user_agents = [
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 11.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.4 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36'
]


# Функция для получения случайного пользовательского агента
def get_random_user_agent():
    return random.choice(user_agents)


# Настройка браузера
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument(f"user-agent={get_random_user_agent()}")
chrome_options.add_argument("--disable-blink-features=AutomationControlled")
chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option("useAutomationExtension", False)

data = []
# Использование webdriver

session = HTMLSession()
response = session.get(
    "https://mos-gorsud.ru/mgs/search?caseDateFrom=16.02.2023&caseDateTo=28.02.2023&courtAlias=mgs&documentStatus=2&processType=6&formType=fullForm&page=2")
time.sleep(3)  # Дополнительная задержка на случай, если нужно, но избегайте чрезмерного использования sleep

soup = BeautifulSoup(response.text, 'html.parser')
heads = soup.find('table', class_='custom_table').find_all('tr')
print(len(heads))
for head in heads[1:]:
    link = 'https://mos-gorsud.ru' + head.find('nobr').find('a')['href']
    print(link)
    loom = session.get(link)
    abble = BeautifulSoup(loom.text, 'html.parser')
    
    documents = abble.find('table', {'class': 'custom_table mainTable'}).find('tbody').find_all('tr')
    for document in documents:
        if "Приговор" in document.text:
            score = document.find_all('td')

            print(len(score))
            for soc in score:
                stock = soc.find_all('a')
                for sto in stock:
                    print('Prigovor: ' + 'https://mos-gorsud.ru' + sto['href'])
                    link_doc = 'https://mos-gorsud.ru' + sto['href']
                    response = requests.get(link_doc, get_random_user_agent())

                    # Проверка успешности запроса
                    if response.status_code == 200:
                        # Сохранение файла на диск
                        with open('prigovor.docx', 'wb') as file:
                            file.write(response.content)

                        # Открытие Word-документа и извлечение текста
                        document = Document('prigovor.docx')
                        text = '\n'.join([paragraph.text for paragraph in document.paragraphs])
                        resheniye = ' '.join(text.split())

                        # Вывод ссылки и текста
                        print('Ссылка на файл: https://mos-gorsud.ru' + sto['href'])
                        print(resheniye)
                    else:
                        print(f"Error downloading file: {response.status_code}")

        elif "Постановление суда апелляционной инстанции" in document.text:
            score = document.find_all('td')

            print(len(score))
            for soc in score:
                stock = soc.find_all('a')
                for sto in stock:
                    print('Postanovleniye : ' + 'https://mos-gorsud.ru' + sto['href'])
                    link_pod = 'https://mos-gorsud.ru' + sto['href']
                    response = requests.get(link_pod, get_random_user_agent())

                    # Проверка успешности запроса
                    if response.status_code == 200:
                        # Сохранение файла на диск
                        with open('resheniye.docx', 'wb') as file:
                            file.write(response.content)

                        # Открытие Word-документа и извлечение текста
                        document = Document('resheniye.docx')
                        text = '\n'.join([paragraph.text for paragraph in document.paragraphs])
                        postanov = ' '.join(text.split())

                        # Вывод ссылки и текста
                        print('Ссылка на файл: https://mos-gorsud.ru' + sto['href'])
                        print(postanov)
                    else:
                        print(f"Error downloading file: {response.status_code}")

            print('\n')

写道：

Traceback (most recent call last):
  File "C:\Users\user\PycharmProjects\cases_pars\little.py", line 143, in <module>
    document = Document('resheniye.docx')
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\user\PycharmProjects\cases_pars\.venv\Lib\site-packages\docx\api.py", line 27, in Document
    document_part = cast("DocumentPart", Package.open(docx).main_document_part)
                                         ^^^^^^^^^^^^^^^^^^
  File "C:\Users\user\PycharmProjects\cases_pars\.venv\Lib\site-packages\docx\opc\package.py", line 127, in open
    pkg_reader = PackageReader.from_file(pkg_file)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\user\PycharmProjects\cases_pars\.venv\Lib\site-packages\docx\opc\pkgreader.py", line 22, in from_file
    phys_reader = PhysPkgReader(pkg_file)
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\user\PycharmProjects\cases_pars\.venv\Lib\site-packages\docx\opc\phys_pkg.py", line 21, in __new__
    raise PackageNotFoundError("Package not found at '%s'" % pkg_file)
docx.opc.exceptions.PackageNotFoundError: Package not found at 'resheniye.docx'

有一个 Flask 项目：

from flask import Flask, request, render_template, send_file
import requests
# import csv
import pandas as pd
from io import BytesIO
import logging
import json
# import pandas as pd
# from io import BytesIO
# -*- coding: utf-8 -*-
import sys

sys.stdout.reconfigure(encoding='utf-8')

logging.basicConfig(level=logging.DEBUG)
app = Flask(__name__)


# Функция для поиска вакансий
def search_vacancies(keyword):
    BASE_URL = "https://api.hh.ru/vacancies"
    vacancies_found = []  # Список для хранения найденных вакансий
    per_page = 100
    page = 0

    while True:
        params = {
            'text': keyword,
            'page': page,
            'per_page': per_page,
            'only_with_salary': True  # Только вакансии с зарплатой
        }

        response = requests.get(BASE_URL, params=params)
        if response.status_code != 200:
            print("Ошибка при обращении к API")
            break

        lan = response.json()

        if not lan['items']:
            break

        for item in lan['items']:
            # vacancy_name = item['name']
            vacancy_name = item['name'].lower()  # Приводим название вакансии к нижнему регистру для сравнения
            # Проверяем, содержит ли название вакансии ключевое слово
            if keyword in vacancy_name:
                salary_from = item['salary']['from'] if item['salary'] else None
                salary_to = item['salary']['to'] if item['salary'] else None
                currency = item['salary']['currency'] if item['salary'] else None
                city = item['area']['name'] if 'area' in item else None
                link = item['alternate_url'] if 'alternate_url' in item else None
                discription = item['snippet']['responsibility'] if 'snippet' in item else None

                vacancies_found.append({
                    'name': vacancy_name,
                    'salary_from': salary_from,
                    'salary_to': salary_to,
                    'currency': currency,
                    'city': city,
                    'link': link,
                    'discription': discription
                })

        page += 1

    return vacancies_found


@app.route('/download', methods=['POST'])
def download():
    keyword = request.form['work_name']
    vacancies = search_vacancies(keyword)

    df = pd.DataFrame(vacancies)
    output = BytesIO()
    df.to_excel(output, index=False)
    output.seek(0)
    return send_file(output, as_attachment=True, download_name='vacancies.xlsx')


@app.route('/', methods=['GET', 'POST'])
def index():
    if request.method == 'POST':
        keyword = request.form['keyword']
        vacancies = search_vacancies(keyword)
        print(len(vacancies))
        all_vacancies = (len(vacancies))
        if vacancies:
            # filename = save_to_json(vacancies)
            return render_template('index.html', vacancies=vacancies, download=True, all_vacancies=all_vacancies)
        else:
            return render_template('index.html', all_vacancies=0)
    return render_template('index.html')


if __name__ == '__main__':
    app.run(debug=True)

<h1>Парсер вакансий</h1>
<form method="POST">
    <label for="keyword">Введите вакансию для поиска:</label>
    <input type="text" id="keyword" style="margin-left: -2%;" name="keyword" required>
    <button type="submit">Искать</button>
</form>
{% if vacancies %}
<h2>Найденные вакансии: {{ all_vacancies }}</h2>
<form method="post" action="/download">
    <input type="hidden" name="work_name" value="{{ keyword }}">
    <input type="submit" value="Скачать в Excel">
</form>
<table>
    <tr>
        <th>Название</th>
        <th>Зарплата от</th>
        <th>Зарплата до</th>
        <th>Валюта</th>
        <th>Город</th>
        <th>Описание</th>
        <th>Ссылка</th>
    </tr>
    {% for vacancy in vacancies %}
    <tr>
        <td>{{ vacancy.name }}</td>
        <td>{{ vacancy.salary_from }}</td>
        <td>{{ vacancy.salary_to }}</td>
        <td>{{ vacancy.currency }}</td>
        <td>{{ vacancy.city }}</td>
        <td>{{ vacancy.discription }}</td>
        <td><a href="{{ vacancy.link }}" class="vacancy-link">{{ vacancy.link }}</a></td>
    </tr>
    {% endfor %}
</table>
{% elif message %}
<p>{{ message }}</p>
{% endif %}
<form method="post" action="/download">
    <input type="hidden" name="work_name" value="{{ keyword }}">
    <input type="submit" value="Скачать в Excel">
</form>
<!--{#</table>#}-->
</body>
</html>

问题是屏幕上显示的解析结果与导出到excel文件的数据不匹配。而且，我对某个关键字请求不同的数据，并且该关键字对应的数据显示在屏幕上，导出到excel文件的数据总是相同的，尽管它必须与屏幕上显示的数据相对应。我不明白为什么会发生这种情况，如果有人知道，请告诉我问题是什么。

项目链接：https://abram742.pythonanywhere.com/

在 Python 代码中使用多个异常仍然会引发错误。如果有人知道请告诉我原因是什么：

import bs4
import time
import requests  # pip install requests
from bs4 import BeautifulSoup  # pip install bs4
from selenium import webdriver  # pip install selenium
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager  # pip install webdriver-manager

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument(
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36')
chrome_options.add_argument("--disable-blink-features=AutomationControlled")

with webdriver.Chrome(service=Service(ChromeDriverManager().install()),
                      options=chrome_options) as driver:  # Открываем хром
    driver.get(f"https://www.stroyportal.ru/catalog/section-bolty-3128/st60/")  # Открываем страницу
    time.sleep(3)  # Время на прогрузку страницы
    soup = bs4.BeautifulSoup(driver.page_source, 'html.parser')
    heads = soup.find('div', class_='col-12 col-xs-12 order-2 order-xs-2 order-sm-2 catalog_list_items').find_all(
        'div', class_='catalog_list_item')
    print(len(heads))
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
    for i in heads:
        try:
            w = i.find_next('div', class_='format_img').find('a', href=True)
            print('https://www.stroyportal.ru' + w['href'])
            get_url = ('https://www.stroyportal.ru' + w['href'])
        except:
            get_url = "https://www.stroyportal.ru/catalog/section-bolty-3128/gayka-soedinitelnaya-m8-702404271/?popup=true"
            break

        stock = requests.get(get_url, headers=headers).text
        moon = BeautifulSoup(stock, 'lxml')
        try:
            name = moon.find('div', class_='font-0 vertical-m').find('h1',
                                                                     class_='d-inline inline-right-16 font-bold font-24')
            print(name.text.strip())
        except Exception:
            name = moon.find('div', class_='col-7 col-sm-6 col-xs-12').find('h1', class_='font-22 font-bold')
            print(name.text.strip())
        except:
            name = 'None'
            print(name)

回溯（最近一次调用最后一次）：文件“C:\Users\user\PycharmProjects\stroyportal_pars\main_3.py”，第 36 行，名称= Moon.find('div', class_='font-0 Vertical-m' ).find('h1', ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^ ^^^^^^ AttributeError：“NoneType”对象没有属性“find”

在处理上述异常的过程中，又出现了一个异常：

回溯（最近一次调用最后一次）：文件“C:\Users\user\PycharmProjects\stroyportal_pars\main_3.py”，第 40 行，名称= Moon.find('div', class_='col-7 col-sm- 6 col-xs-12').find('h1', class_='font-22 font-bold') ^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError：“NoneType”对象没有属性“find”

有一个用于注册汽车和驾驶员的Python程序。
问题是只执行了第一部分，第二部分抛出错误。

我不明白出了什么问题。如果有人知道，请告诉我。

我的代码：

class Car:
    def __init__(self, license_plate, brand, model, color):
        self.license_plate = license_plate
        self.brand = brand
        self.model = model
        self.color = color


class Driver:
    def __init__(self, name, age, license_number):
        self.name = name
        self.age = age
        self.license_number = license_number


class ParkingLot:
    def __init__(self):
        self.cars = []
        self.drivers = []

    def add_car(self, car):
        self.cars.append(car)
        print(f"Машина {car.license_plate} добавлена в учет.")

    def add_driver(self, driver):
        self.drivers.append(driver)
        print(f"Водитель {driver.name} добавлен в учет.")

    def remove_car(self, car):
        self.cars.remove(car)
        print(f"Машина {car.license_plate} удалена из учета.")

    def remove_driver(self, driver):
        self.drivers.remove(driver)
        print(f"Водитель {driver.name} удален из учета.")

    def get_car_by_license_plate(self, license_plate):
        for car in self.cars:
            if car.license_plate == license_plate:
                return car
        return None

    def get_driver_by_license_number(self, license_number):
        for driver in self.drivers:
            if driver.license_number == license_number:
                return driver
        return None


while True:
    # Пример использования программы
    parking_lot = ParkingLot()
    print('enter number car')
    nu_car = input()
    print('enter color car')
    color = input()
    print('enter firm car')
    firm_car = input()
    print('enter model car')
    model = input()
    print('enter first last name')
    name = input()
    print('enter age driver')
    age = int(input())
    print('enter drivedoc')
    docc = int(input())
    car1 = Car(f"{nu_car}", f"{firm_car}", f"{model}", f"{color}")
    driver1 = Driver(f"{name}", f"{age}", f"{docc}")
    print('Выберите соответсвующую цифру: 1-добавить в учёт, 2-удалить из учёта')
    count = int(input())
    if count == 1:
        # Добавляем машину и водителя в учет
        parking_lot.add_car(car1)
        parking_lot.add_driver(driver1)
    elif count == 2:
        # Удаляем машину и водителя из учета
        parking_lot.remove_car(car1)
        parking_lot.remove_driver(driver1)

数据不写入excel表，只写入最后一行。尝试了不同的位置，结果相同。如果有人知道，请告诉我错误在哪里？

import pandas as pd
import requests
from bs4 import BeautifulSoup

while True:
    print('Выберите категорию товара: легковые шины, грузовые шины, внедорожные шины')
    name = input()
    if name == 'легковые шины':
        get_name = 'https://samara.express-shina.ru/search/legkovyie-shinyi'
    elif name == 'грузовые шины':
        get_name = 'https://samara.express-shina.ru/search/gruzovyie-shinyi'
    elif name == 'внедорожные шины':
        get_name = 'https://samara.express-shina.ru/search/vnedorozhnyie-shinyi'
    else:
        print('Такой категории нет')

    print('Введите название файла латинскими буквами')
    file_name = str(input())

    count = 1
    while count <= 3:
        url = f'{get_name}?num={count}'
        data = requests.get(url).text
        block = BeautifulSoup(data, 'lxml')
        heads = block.find_all('div', class_='b-offer__boxes')
        for i in heads:
            get_url = i.find_next('a').get('href')
            # print('https://samara.express-shina.ru'+get_url)
            w = ('https://samara.express-shina.ru' + get_url)
            seac = requests.get(w).text
            look = BeautifulSoup(seac, 'lxml')
            leen = look.find('div', class_='header_product_page').find('h1')
            print(leen.text.strip())
            nazvan = (leen.text.strip())
            price = look.find('span', class_='price_new')
            print(price.text.strip())
            cena = (price.text.strip())
            articul = look.find('span', class_='articul')
            print(articul.text.strip())
            codde = (articul.text.strip())
            img = look.find('div', class_='inner_images').find('img').get('src')
            print('https://samara.express-shina.ru' + img)
            pixx = ('https://samara.express-shina.ru' + img)
            print('\n')

            storage = {'zagol': nazvan,
                       'cena': cena,
                       'articul': codde,
                       'img': pixx}

            df = pd.DataFrame({
                'NAME': [storage['zagol']],
                'PRICE': [storage['cena']],
                'ARTICUL': [storage['articul']],
                'IMG': [storage['img']]
            })
            df.to_excel(f'{file_name}.xlsx')

        count += 1