爬虫-关于58同城繁体字解析

import re
import base64
from io import BytesIO
from fontTools.ttLib import TTFont
import requests
from lxml import etree

session = requests.session()
response = session.get(url='https://bj.58.com/chuzu/')
bs64_str = re.findall("charset=utf-8;base64,(.*?)'\)", response.text)[0]

def get_page_show_ret(string):
    font = TTFont(BytesIO(base64.decodebytes(bs64_str.encode())))
    c = font['cmap'].tables[0].ttFont.tables['cmap'].tables[0].cmap
    ret_list = []
    for char in string:
        decode_num = ord(char)
        if decode_num in c:
            num = c[decode_num]
            num = int(num[-2:])-1
            ret_list.append(num)
        else:
            ret_list.append(char)
    ret_str_show = ''
    for num in ret_list:
        ret_str_show += str(num)
    return ret_str_show

将爬取的数据遍历调用上面的函数就可以解析

monery = html.xpath('//div/ul/li/div[3]/div[2]/b/text()')[:10]
price = []
for i in monery:
    p = get_page_show_ret(i)
    price.append(p)