Question

我试图从网站获取数据并将其输入到 csv 中

table_array = []

def get_data(page):
    url = "https://www.sl886.com/stockrating/list?list=stockrating&page=" + str(page)

    get = requests.get(url, headers=headers)

    table_bs4 = BeautifulSoup(get.text, "html.parser")

    main_table = table_bs4.find("table").find("tbody")

    for i in main_table.find_all("tr"):
        array = []
        for x in i.find_all("td"):
            array.append(x.text)
            print(x.text, end = " ")
        table_array.append(array[:-1])
        print("")

def get_page_number():
    url = "https://www.sl886.com/stockrating/list?list=stockrating&page=1"

    get = requests.get(url, headers=headers)
    
    table_bs4 = BeautifulSoup(get.text, "html.parser")

    sum_of_items = table_bs4.find("div", {"class": "summary"})
    sum_of_items = int(sum_of_items.find_all("b")[1].text.replace(",", ""))

    total_pages = math.ceil(sum_of_items/20)
    
    return total_pages

运行：

for i in range(1):#range(get_page_number()):
    get_data(i + 9)

with open("big_bank_rating.csv", "w", newline="") as csvfile:
    write = csv.writer(csvfile)

    write.writerow(["日期", "大行", "股票", "最新評級", "目標價", "變化", "潛在升幅"])

    for xi in table_array:
        print(xi)

    write.writerows(table_array)
    print("!!!Done Append!!!")

但是出现编码错误

Traceback (most recent call last):
  File "data_crawl.py", line 55, in <module>
    write.writerows(table_array)
UnicodeEncodeError: 'cp950' codec can't encode character '\u7dab' in position 19: illegal multibyte sequence

我尝试使用编码“uft-8”，但得到的结果是乱码。我该如何解决？对字符 '\u7dab' 进行编码

Answer 1

我必须使用

encoding="utf_8_sig"

如何修复“UnicodeEncodeError: 'cp950' codec can't encode character '\u7dab' in position 19:非法多字节序列”

1 个答案: