Python UnicodeEncodeError:“cp949”编解码器无法对位置90中的字符“\u20a9”进行编码：非法的多字节序列

我是python初学者

我正在尝试抓取google play商店并导出到csv文件。 但我收到一条错误信息

UnicodeEncodeError: 'cp949' codec can't encode character '\u20a9' in position 90: illegal multibyte sequence

这是我的源代码

当我命令print时，它就工作了。 但在导出到csv文件时会显示错误消息

请帮帮我

from bs4 import BeautifulSoup
import urllib.request
import urllib.parse
import codecs
import json
import pickle
from datetime import datetime
import sys
import csv
import os


req = 'https://play.google.com/store/search?q=hana&c=apps&num=300'



response = urllib.request.urlopen(req)
the_page = response.read()
soup = BeautifulSoup(the_page)


#app_link  = soup.find('a', {'class' : 'title'})
#app_url = app_link.get('href')





for div in soup.findAll( 'div', {'class' : 'details'} ):
    title = div.find( 'a', {'class':'title'} )
    #print(title.get('href')) 
    app_url = title.get('href')

    app_details={}


    g_app_url = 'https://play.google.com' + app_url

    app_response = urllib.request.urlopen(g_app_url)
    app_page = app_response.read()
    soup = BeautifulSoup(app_page)
    #print(soup)


    #print( g_app_url )
    title_div = soup.find( 'div', {'class':'document-title'} )
    app_details['title'] = title_div.find( 'div' ).get_text().strip()

    subtitle = soup.find( 'a', {'class' : 'document-subtitle primary'} )
    app_details['developer'] = subtitle.get_text().strip()
    app_details['developer_link'] = subtitle.get( 'href' ).strip()

    price_buy_span = soup.find( 'span', {'class' : 'price buy'} )
    price = price_buy_span.find_all( 'span' )[-1].get_text().strip()
    price = price[:-4].strip() if price != 'Install' else 'Free' 
    app_details['price'] = price

    rating_value_meta = soup.find( 'meta', {'itemprop' : 'ratingValue'} )
    app_details['rating'] = rating_value_meta.get( 'content' ).strip()

    reviewers_count_meta = soup.find( 'meta', {'itemprop' : 'ratingCount'} )
    app_details['reviewers'] = reviewers_count_meta.get( 'content' ).strip()

    num_downloads_div = soup.find( 'div', {'itemprop' : 'numDownloads'} )
    if num_downloads_div: app_details['downloads'] = num_downloads_div.get_text().strip()

    date_published_div = soup.find( 'div', {'itemprop' : 'datePublished'} )
    app_details['date_published'] = date_published_div.get_text().strip()

    operating_systems_div = soup.find( 'div', {'itemprop' : 'operatingSystems'} )
    app_details['operating_system'] = operating_systems_div.get_text().strip()

    content_rating_div = soup.find( 'div', {'itemprop' : 'contentRating'} )
    app_details['content_rating'] = content_rating_div.get_text().strip()

    category_span = soup.find( 'span', {'itemprop' : 'genre'} )
    app_details['category'] = category_span.get_text()
    #print(app_details)


    with open('result.csv', 'w') as f:  # Just use 'w' mode in 3.x
        w = csv.DictWriter(f, app_details.keys())
        w.writeheader()
        w.writerow(app_details)

---

Python3以区域设置默认编码打开文本文件；如果该编码无法处理您试图写入的Unicode值，请选择其他编解码器：

with open('result.csv', 'w', encoding='UTF-8', newline='') as f:

这会将任何unicode字符串编码为UTF-8，这种编码可以处理所有unicode标准

请注意，csv模块建议您使用换行符=打开文件，以防止换行符转换

您还需要在for循环之外只打开一次文件：

---

谢谢：我还有一个关于csv结果的问题。我尝试了代码并打开了“result.csv”文件。我发现只有一行是最后一个循环结果。你能解释一下为什么它会存储最后一个循环结果吗？？？@user3172987：你每次循环迭代都会重新打开csv文件，这会清除文件并开始一个新的循环。每次迭代。将打开文件移出循环，包括创建DictWriter对象和调用w.writeheader，并且只在循环中调用w.writerow。@user3172987:Done；给DictWriter一个你想先写的密钥列表。

with open('result.csv', 'w') as f:  # Just use 'w' mode in 3.x
    fields = ('title', 'developer', 'developer_link', 'price', 'rating', 'reviewers',
              'downloads', 'date_published', 'operating_system', 'content_rating',
              'category')
    w = csv.DictWriter(f, )
    w.writeheader()

    for div in soup.findAll( 'div', {'class' : 'details'} ):
        #
        # build app_details
        #

        w.writerow(app_details)