黄兵的个人博客

python写入csv文件中文乱码解决方案

今天修改程序，需要写入csv文件，发现中文会乱码，后来查了下，可以设置文件写入属性后，就可以解决：

# -*- coding: utf-8 -*-

import csv
import pyodbc
import lxml.html
from link_crawler import link_crawler
from datetime import datetime
import sys
import codecs

reload(sys)
sys.setdefaultencoding('utf8')
class ScrapeCallback:
    def __init__(self):
        self.writer = csv.writer(open('countries.csv', 'w'))
        self.fields = ('title','context')
        self.writer.writerow(self.fields)

    def __call__(self, url, html):
        tree = lxml.html.fromstring(html)
        #conn = pyodbc.connect(r'DRIVER={SQL Server Native Client 10.0};SERVER=14;DATABASE=m;UID=Faa;PWD=hu18')
        #cursor = conn.cursor()
        #cursor.execute("INSERT INTO Articles (Title, CreateTime,Reader,ArticleBody,Category_Id,SEOId,AuthorId,Topic,ImgUrl,News,FirstProject,SecondProject)VALUES (\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\")",
                       # (title,datetime.now(),0,context,'',6,1,0,'',0,0,0))
        #cursor.execute("insert into Articles(Title, CreateTime,Reader,ArticleBody,Category_Id,SEOId,AuthorId,Topic,ImgUrl,News,FirstProject,SecondProject) values (title,datetime.now(),0,context,,6,1,0,,0,0,0 )")
        #conn.commit()
        #cursor.execute("SELECT * FROM Articles")
        #rows = cursor.fetchall()
        #for row in rows:
         #   print(row.Title, row.ArticleBody)
        row = []
        for trees in tree.cssselect('#essay_xb_C'):
            title=trees.cssselect('.essay_xb_tle > h2')[0].text_content()
            context=trees.cssselect('.text_C')[0].text_content()
            row.append([title,context])
            print(row)
            with open('countries.csv', 'w') as f:
                writer = csv.writer(f)
                f.write(codecs.BOM_UTF8)
                writer.writerow(['title','context'])
                for rows in row:
                    print(rows)
                    writer.writerow(rows)
        #for field in self.fields:
         #   row.append(title,context)
        #elf.writer.writerow(row)

if __name__ == '__main__':
    link_crawler('http://www.mylikesz.com/', '/(html|view)', scrape_callback=ScrapeCallback())

最为关键的一句就是：csvfile.write(codecs.BOM_UTF8)，有了这一句，中文就能正常写入

参考资料：python写入csv文件中文乱码解决方案