pycharm报错An error occurred: 'gb18030' codec can't decode byte 0x8b in position 1

Question

pycharm报错An error occurred: 'gb18030' codec can't decode byte 0x8b in position 1: illegal multibyte sequence

# -*- coding: utf-8 -*-
from urllib import request
from lxml import etree
import csv
def initUrs():
    urls = ['https://www.jjwxc.net/bookbase.php?fw0=0&fbsj0=0&xx0=0&mainview0=0&sd0=0&lx0=0&fg0=0&bq=-1&sortType=4&isfinish=0&collectiontypes=ors&searchkeywords=&page=3']
    return urls
def get(urls):
    for url in urls:
        try:
            data = request.urlopen(url).read().decode('gb18030')
            pData = parse(data)
            out(pData)
        except request.HTTPError as e:
            print(f"HTTP error: {e}")
        except request.URLError as e:
            print(f"URL error: {e}")
        except etree.XPathSyntaxError as e:
            print(f"XPath syntax error: {e}")
        except Exception as e:
            print(f"An error occurred: {e}")
def parse(data):
    pData = etree.HTML(data)
    items = pData.xpath('//tr')[1:]
    itemDatas = []
    for item in items:
        itemData = {}
        tds = item.xpath('./td')
        texts = tds[0].xpath('./a//text()')
        itemData['作者'] = '' if(len(texts) == 0) else texts[0]
        texts = tds[1].xpath('./a//text()')
        itemData['书名'] = '' if(len(texts) == 0) else texts[0]
        texts = tds[2].xpath('.//text()')
        itemData['类型'] = '' if len(texts) == 0 else texts[0].strip().replace('\n', '')
        # .replace('-', '') 去除 原创-纯爱-近代现代-剧情 中的-
        texts = tds[3].xpath('./font//text()')
        itemData['进度'] = '' if(len(texts) == 0) else texts[0]
        texts = tds[4].xpath('.//text()')
        itemData['字数'] = '' if(len(texts) == 0) else texts[0]
        texts = tds[5].xpath('.//text()')
        itemData['积分'] = '' if(len(texts) == 0) else texts[0]
        itemDatas.append(itemData)
    return itemDatas
# 输出并且保存为csv文档
def out(data):
    print(data)
    with open('xiaoshuo3.csv', 'w',encoding='gb18030',newline='') as f:
        csvf = csv.DictWriter(f, fieldnames=['作者', '书名', '类型','进度','字数','积分'])
        csvf.writeheader()
        csvf.writerows(data)
get(initUrs())

怎么解决

Answer 1

【以下回答由 GPT 生成】

这个问题是因为使用gb18030编码解码字节时，出现了非法的多字节序列，在Python中可以使用utf-8编码替代gb18030进行解码。

以下是修改后的代码示例：

# -*- coding: utf-8 -*-
from urllib import request
from lxml import etree
import csv

def initUrs():
    urls = ['https://www.jjwxc.net/bookbase.php?fw0=0&fbsj0=0&xx0=0&mainview0=0&sd0=0&lx0=0&fg0=0&bq=-1&sortType=4&isfinish=0&collectiontypes=ors&searchkeywords=&page=3']
    return urls

def get(urls):
    for url in urls:
        try:
            data = request.urlopen(url).read().decode('utf-8')  # 将编码改为utf-8
            pData = parse(data)
            out(pData)
        except request.HTTPError as e:
            print(f"HTTP error: {e}")
        except request.URLError as e:
            print(f"URL error: {e}")
        except etree.XPathSyntaxError as e:
            print(f"XPath syntax error: {e}")
        except Exception as e:
            print(f"An error occurred: {e}")

def parse(data):
    pData = etree.HTML(data)
    items = pData.xpath('//tr')[1:]
    itemDatas = []
    for item in items:
        itemData = {}
        tds = item.xpath('./td')
        texts = tds[0].xpath('./a//text()')
        itemData['作者'] = '' if len(texts) == 0 else texts[0]
        texts = tds[1].xpath('./a//text()')
        itemData['书名'] = '' if len(texts) == 0 else texts[0]
        texts = tds[2].xpath('./span/text()')
        itemData['评分'] = '' if len(texts) == 0 else texts[0]
        itemDatas.append(itemData)
    return itemDatas

通过修改decode('gb18030')为decode('utf-8')，可以解决该问题。如果还有其他问题，请及时反馈，我会尽力提供帮助。

【相关推荐】

• 建议你看下这篇博客👉 ：pycharm 读取文件出现错误UnicodeDecodeError: ‘gbk‘ codec can‘t decode byte 0x8c in position 3: illegal multib

如果你已经解决了该问题, 非常希望你能够分享一下解决方案, 写成博客, 将相关链接放在评论区, 以帮助更多的人 ^-^