python - 统一码编码错误 : 'cp949' codec can't encode character '\u20a9' in position 90: illegal multibyte sequence

Question

我是 python 初学者。

我正在尝试抓取 google play 商店并导出到 csv 文件。 但是我收到一条错误消息。

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

这是我的源代码。

当我命令打印时，它起作用了。 但在导出到 csv 文件时显示错误消息

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)

Answer 1

Python 3 以语言环境默认编码打开文本文件；如果该编码无法处理您尝试写入的 Unicode 值，请选择不同的编解码器:

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

这会将任何 unicode 字符串编码为 UTF-8，一种可以处理所有 Unicode 标准的编码。

请注意，csv 模块建议您使用 newline='' 打开文件以防止换行符转换。

您还需要在 for 循环之外只打开文件一次:

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)