[已解决]UnicodeDecodeError: 'utf-8' codec can't decode byte 0xbb in position 65: inva...

白卷i

萌新学习爬取网站图片，但网站编码不了‘utf-8’，怎么办，请求各位大佬指点迷津！

import urllib.request
import os

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36 Edg/97.0.1072.69')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html
   
def find_imgs(url):
    print(url)
    html = url_open(url).decode("utf-8")  #报错的位置
    print(html)
   
    img_addrs = []

    a = html.find('img alt')
    b = html.find('src=',a)
    c = html.find('.jpg',b,b+255)

    if c !=-1:
        img_addrs.append(html[b+5:c+4])

    for each in img_addrs:
        print(each)

def save_imgs(folder,img_addrs):
    pass

def download_photo(folder = 'photo',pages = 10):
    try:
        os.mkdir(folder)
    except FileExistsError:
         pass
    os.chdir(folder)

    url = "http://www.daimg.com/photo/"
    page_num = int(220622)

    for i in range(10):
        page_num += i
        page_url = url + '202202/photo_' + str(page_num) + '.html'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)

if __name__=='__main__':
    download_photo()

Python 3.6.5 (v3.6.5:f59c0932b4, Mar 28 2018, 17:00:18) [MSC v.1900 64 bit (AMD64)] on win32
Type "copyright", "credits" or "license()" for more information.
>>>
============== RESTART: D:\python-3.6.5-amd64\download_photo.py ==============
http://www.daimg.com/photo/202202/photo_220622.html
Traceback (most recent call last):
  File "D:\python-3.6.5-amd64\download_photo.py", line 48, in <module>
    download_photo()
  File "D:\python-3.6.5-amd64\download_photo.py", line 44, in download_photo
    img_addrs = find_imgs(page_url)
  File "D:\python-3.6.5-amd64\download_photo.py", line 13, in find_imgs
    html = url_open(url).decode("utf-8")
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xbb in position 65: invalid start byte

最佳答案

月排行榜 / 总排行榜

isdkz

2022-3-18 13:47:49

那就改成 gbk 呗

import urllib.request
from urllib.request import HTTPError
import os

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36 Edg/97.0.1072.69')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html
   
def find_imgs(url):
    print(url)
    html = url_open(url).decode("gbk")  #报错的位置
    print(html)
   
    img_addrs = []

    a = html.find('img alt')
    b = html.find('src=',a)
    c = html.find('.jpg',b,b+255)

    if c !=-1:
        img_addrs.append(html[b+5:c+4])

    for each in img_addrs:
        print(each)

def save_imgs(folder,img_addrs):
    pass

def download_photo(folder = 'photo',pages = 10):
    try:
        os.mkdir(folder)
    except FileExistsError:
         pass
    os.chdir(folder)

    url = "http://www.daimg.com/photo/"
    page_num = int(220622)

    for i in range(10):
        page_num += i
        page_url = url + '202202/photo_' + str(page_num) + '.html'
        try:
            img_addrs = find_imgs(page_url)
        except HTTPError:
            continue
        save_imgs(folder,img_addrs)

if __name__=='__main__':
    download_photo()

跳转到最佳答案楼层

isdkz

那就改成 gbk 呗

import urllib.request
from urllib.request import HTTPError
import os

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36 Edg/97.0.1072.69')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html
   
def find_imgs(url):
    print(url)
    html = url_open(url).decode("gbk")  #报错的位置
    print(html)
   
    img_addrs = []

    a = html.find('img alt')
    b = html.find('src=',a)
    c = html.find('.jpg',b,b+255)

    if c !=-1:
        img_addrs.append(html[b+5:c+4])

    for each in img_addrs:
        print(each)

def save_imgs(folder,img_addrs):
    pass

def download_photo(folder = 'photo',pages = 10):
    try:
        os.mkdir(folder)
    except FileExistsError:
         pass
    os.chdir(folder)

    url = "http://www.daimg.com/photo/"
    page_num = int(220622)

    for i in range(10):
        page_num += i
        page_url = url + '202202/photo_' + str(page_num) + '.html'
        try:
            img_addrs = find_imgs(page_url)
        except HTTPError:
            continue
        save_imgs(folder,img_addrs)

if __name__=='__main__':
    download_photo()

白卷i

isdkz 发表于 2022-3-18 13:47
那就改成 gbk 呗

谢谢大佬，问题解决了，等学完了基本语法，就去了解一下编码，