Question

我使用sqlite存储某些股票的一系列价格我无法登录该网站，所以我在本地保存了多次网页以跟踪不同的价格。

我的代码现在适用于我之前制作的两个保存，但是当我尝试使用今天的任何保存时，我收到以下错误

UnicodeDecodeError: 'charmap' codec can't decode byte 0x90 in position 415367:character maps to <undefined>

我的代码如下

from bs4 import BeautifulSoup
from time import gmtime, strftime
import sqlite3
from sqlclean import *
count = 0
def create_tables(stock):
sql_command = """CREATE TABLE """ + stock +"""(
              Stock_number INTEGER PRIMARY KEY,
              BuyPrice REAL,
              SellPrice REAL,
              Time VARCHAR(30));"""
cursor.execute(sql_command)



def fill():
    y = 0
    for i in stock:
    string = sqstring(i)
    stock[y] = string
    y = y + 1 
    for i in stock:
        create_tables(str(i))




def populate():
    x = 0
    for i in stock:
        cursor.execute("""
            INSERT INTO """+ i +"""
            (SellPrice,BuyPrice)
            VALUES
            (""" + sell[x]+""","""+ buy[x] +""")
            """)
        x = x + 1

def get_stocks(soup):
    global count
    rep1 = 0
    rep2 = 0
    if count == 0:
        count = count + 1
        for price in soup.find_all('span',{"class" : "tbox-list-button-sell"}):
            sell.append(price.text)
        for price in soup.find_all('span',{"class" : "tbox-list-button-buy"}):
             buy.append(price.text)
        for price in soup.find_all('div',{"class" : "window_title list-title"}):
             a = price.text.strip()
            stock.append(a)
        fill()
        populate()
    else:
        for price in soup.find_all('span',{"class" : "tbox-list-button-sell"}):
            sell[rep1] = (price.text)
            rep1 = rep1 + 1
        for price in soup.find_all('span',{"class" : "tbox-list-button-buy"}):
            buy[rep2] = (price.text)
            rep2 = rep2 + 1

        populate()



connection = sqlite3.connect("stocks.db")


cursor = connection.cursor()

web = ["C:/Users/Luke_2/Desktop/Computing/Coursework/Practice/Stocks1/demo.trading212.com.html","C:/Users/Luke_2/Desktop/Computing/Coursework/live/Stocks1/demo.trading212.com1.html","C:/Users/Luke_2/Desktop/Computing/Coursework/live/Stocks1/demo.trading212.com10.24.html"]   
stock=[]
sell = []
buy = []

def run():
    for i in web:
        soup = BeautifulSoup(open(i),"html.parser")
        get_stocks(soup)
run()

connection.commit()

connection.close()

Answer 1

你没有告诉open（）函数在阅读文件时使用什么编解码器，例如如果您在文件中使用utf-8：

在Python 2.7中：

import io
...
def run():
    for i in web:
        with io.open(i, encoding='utf-8') as infile:
            soup = BeautifulSoup(infile,"html.parser")

对于Python3

def run():
    for i in web:
        with open(i, encoding='utf-8') as infile:
            soup = BeautifulSoup(infile,"html.parser")

为什么这个错误只出现在我今天的网页上，而不是昨天

1 个答案: