爬虫编码

ZQLSTC

import urllib.request
import os

def url_open(url):
    res = urllib.request.Request(url)
    res.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36")
    response = urllib.request.urlopen(res)
    html = response.read()
    return html

def find_img(url):
    html = url_open(url).decode("utf-8")
    a = html.find("img src=")
    img_addrs=[]
    while a!=-1:
        b = html.find('id="bigpicimg"',a,a+255)
        if b==-1:
            img_addrs.append(html[a+9:b-2])
        else :
            b=a
        a = html.find("img src=",b)
        
    for i in img_addrs:
        print(i)
    


def download(folder = "chengduling",page = 5):
    os.mkdir(folder)
    os.chdir(folder)

    url="http://www.tupianzj.com/mingxing/xiezhen/20180625/"
    for i in range(1,6):
        if i==1:
            page_num = "163771"
        else:
            page_num = "163771"+"_"+str(i)
        page_url = url + page_num + ".html"
        img_url = find_img(page_url)


if __name__ == "__main__":
    download()

Traceback (most recent call last):
  File "C:/Users/123/Desktop/chengduling.py", line 43, in <module>
    download()
  File "C:/Users123/Desktop/chengduling.py", line 39, in download
    img_url = find_img(page_url)
  File "C:/Users/123/Desktop/chengduling.py", line 12, in find_img
    html = url_open(url).decode("utf-8")
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb3 in position 309: invalid start byte

编码报错要怎么解决

拉了盏灯

应该是有中文，decode('gbk')试试

我爱鱼C！

html = url_open(url).decode("GB2312")
改成这个试试

小小小小的鱼丶

def url_open(url):
    res = urllib.request.Request(url)
    res.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36")
    response = urllib.request.urlopen(res)
#这里加一句
   response.encoding='utf-8'
    html = response.read()
    return html