如何将main()函数的运行结果输出为CSV文件并解决西里尔字符乱码问题

核心问题梳理 #

• 无法输出CSV：你的main()函数最后仅执行了print(df)操作，没有使用return返回构造完成的DataFrame对象，调用main()时拿到的是空值，自然无法写入文件。
• 西里尔文本乱码：一是原代码直接将BeautifulSoup解析得到的Tag对象存入列表，没有提取标签内的纯文本内容；二是编码选择不合理，cp1251是俄语西里尔编码，你爬取的是蒙古语西里尔站点，直接用utf-8-sig编码兼容性更强，既可以保证字符正确存储，用Excel打开也不会出现乱码。
• 额外隐藏问题：原代码在循环内部重复构造DataFrame，还存在commission_year重复追加的逻辑，会导致列长度不匹配报错。

修正后的完整代码 #

import requests
from bs4 import BeautifulSoup as BS
from datetime import datetime
import pandas as pd
import re
import csv

today = datetime.today().strftime('%y%m%d ')

def main():
    page = 0
    name = []
    date = []
    address = []
    district = []
    city = []
    price = []
    area_sqm = []
    rooms = []
    floor = []
    commission_year = []
    building_floors = []
    garage = []
    balcony = []
    windows = []
    window_type = []
    floor_type = []
    door_type = []
    leasing = []
    description = []
    link = []

    BASE = 'https://www.unegui.mn'
    URL = f'{BASE}/l-hdlh/l-hdlh-zarna/oron-suuts-zarna/5-r/?page='
    COLUMNS=['Name','Date','Address','District','City','Price','Area_sqm','Rooms','Floor','Commission_year',
             'Building_floors','Garage', 'Balcony','Windows','Window_type','Floor_type','door_type','Leasing','Description','Link']
    with requests.Session() as session:
        while True:
            r = session.get(f'{URL}{page+1}')
            r.raise_for_status()
            m = re.search('.*page=(\d+)$', r.url)
            if m and int(m.group(1)) == page:
                break
            page += 1
            print(f'Scrapping page {page}')
            soup = BS(r.text, 'lxml')
            for tag in soup.findAll('div', class_='list-announcement-block'):
                _name = tag.find('a', attrs={'itemprop': 'name'})
                name.append(_name.get('content', 'N/A'))
                if (_link := _name.get('href', None)):
                    link.append(f'{BASE}{_link}')
                    _r = session.get(link[-1])
                    _r.raise_for_status()
                    detail_soup = BS(_r.text, 'lxml')
                    _spanlist = detail_soup.find_all('span', class_='value-chars')
                    # 提取Tag对象的纯文本，加长度判断避免字段缺失报错
                    floor_type.append(_spanlist[0].get_text(strip=True) if len(_spanlist)>=1 else 'N/A')
                    balcony.append(_spanlist[1].get_text(strip=True) if len(_spanlist)>=2 else 'N/A')
                    garage.append(_spanlist[2].get_text(strip=True) if len(_spanlist)>=3 else 'N/A')
                    window_type.append(_spanlist[3].get_text(strip=True) if len(_spanlist)>=4 else 'N/A')
                    door_type.append(_spanlist[4].get_text(strip=True) if len(_spanlist)>=5 else 'N/A')    
                    windows.append(_spanlist[5].get_text(strip=True) if len(_spanlist)>=6 else 'N/A')
                    
                    _alist = detail_soup.find_all('a', class_='value-chars')
                    commission_year.append(_alist[0].get_text(strip=True) if len(_alist)>=1 else 'N/A')
                    building_floors.append(_alist[1].get_text(strip=True) if len(_alist)>=2 else 'N/A')
                    area_sqm.append(_alist[2].get_text(strip=True) if len(_alist)>=3 else 'N/A')
                    floor.append(_alist[3].get_text(strip=True) if len(_alist)>=4 else 'N/A')
                    leasing.append(_alist[4].get_text(strip=True) if len(_alist)>=5 else 'N/A')
                    district.append(_alist[5].get_text(strip=True) if len(_alist)>=6 else 'N/A')
                    address.append(_alist[6].get_text(strip=True) if len(_alist)>=7 else 'N/A')
                    
                rooms.append(tag.find('div', attrs={'announcement-block__breadcrumbs'}).get_text().split('»')[1].strip())
                description.append(tag.find('div', class_='announcement-block__description').get_text().strip())
                date.append(tag.find('div', class_='announcement-block__date').get_text().split(',')[0].strip())
                city.append((tag.find('meta', attrs={'itemprop': 'areaServed'})).get('content'))
                if (_price := tag.find('meta', attrs={'itemprop': 'price'})) is None:
                    _price = tag.find('div', class_='announcement-block__price _premium')
                price.append(_price.get_text().strip() if _price else 'N/A')
        # 循环结束后统一构造完整DataFrame并返回
        df = pd.DataFrame(list(zip(name, date, address, district, city, 
                              price, area_sqm, rooms, floor, commission_year,
                              building_floors, garage, balcony, windows, window_type,
                              floor_type, door_type, leasing, description, link)), columns=COLUMNS)
        print(df)
        return df

if __name__ == '__main__':
    df = main()
    # 使用utf-8-sig编码保证西里尔字符正常显示，Excel打开也不会乱码
    df.to_csv(f'{today}HPD.csv', encoding='utf-8-sig', index=False)

内容的提问来源于stack exchange，提问作者WX1505