遇到关于''.join吃字符串的问题

Question

import requests
from lxml import etree
from urllib.parse import urljoin
import queue
# import threading
# import time


new_headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36"
               }
url = 'http://www.biqugev.com/book/40234/'

r = requests.get(url, headers=new_headers)
r.encoding = r.apparent_encoding

html = etree.HTML(r.text)
b = html.xpath("//div[@class='listmain']/dl/dd/a/@href")
b = [urljoin(url,i) for i in b]


q = queue.Queue()
for num in range(len(b)):
    qa = dict()
    qa['n'] = num
    qa['url'] = b[num]
    q.put(qa)


def parse_text(n, url):
    # print(n)
    r = requests.get(url,headers=new_headers)
    # print(r.status_code,r.encoding)
    html = etree.HTML(r.text)
    bb = html.xpath("//div[@class='content']/h1/text()")[0]
    aa = html.xpath("//div[@class='content']/div[@id='content']/text()")
    print(aa)
    # print(bb)
    aa = ''.join(aa)
    print('合起来:', aa)
    # time.sleep(1)

d = q.get()

parse_text(d['n'],d['url'])

Answer 1

加一行代码
print(len(aa))
可以看到，aa的长度很长，由此可以判断没有发送你所说的”吃字符串“的问题

在加一行代码

repr(aa)

可以看到字符中有大量的特殊符号，导致部分内容显式不出来