写入txt文件时出现乱码
#-*- codeing = utf-8 -*-import urllib.request
import re
#import xlwt
import bs4
def main():
url = 'https://www.qiushibaike.com/text/page/'
saveData('糗事百科段子.txt', getData(url))
def url_open(url):
head = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'}
req = urllib.request.Request(url, headers=head)
html = ""
try:
response = urllib.request.urlopen(req)
html = response.read().decode('utf-8')
except urllib.error.URLError as e:
if hasattr(e, 'code'):
print(e.code)
if hasattr(e, 'reason'):
print(e.reason)
return html
def getData(url):
html = url_open(url)
bs = bs4.BeautifulSoup(html, 'html.parser')
t_list = bs.find_all('div', attrs = {'class' : 'content'})
text_list = []
#t_list = bs.find_all(text = 'span')
for item in t_list:
text_list.append(item.find('span').text)
return text_list
def saveData(fileurl, t_list):
for each in t_list:
with open(fileurl, 'a+', encoding = 'utf-8') as f:
f.write(each)
if __name__ == "__main__":
main()
以上代码时我从糗事百科中爬出来的段子,把爬出来的内容写入txt文件,在txt文件中出现乱码
https://s1.ax1x.com/2020/09/03/wCllwV.png
大神门看看我！！！ 试了一下，没有遇到乱码问题，楼主尝试重新运行一下 1q23w31 发表于 2020-9-3 11:41
试了一下，没有遇到乱码问题，楼主尝试重新运行一下
的确我把txt文件删除重新写入就没有这样的问题了
页:
[1]