关于python crawler的一些问题

Question

我几天前学习了python crawler，然后做了一些练习。但我遇到了一个问题，我不知道如何解决它。

from bs4 import BeautifulSoup
import requests
import time


def crawler(url, data=None):
    wb_data = requests.get(url)
    time.sleep(2)
    soup = BeautifulSoup(wb_data.text, 'lxml')
    headers = soup.select('div.pho_info > h4 > em')
    addresses = soup.select('div.pho_info > p > span.pr5')
    prices = soup.select('#pricePart > div.day_l > span')
    images1 = soup.select('#curBigImage')
    images2 = soup.select('div.member_pic > a > img')
    names = soup.select('div.w_240 > h6 > a')
    genders = soup.select('div.member_pic > div')

    def crawl_gender(a):
        if a == 'member_ico1':
            return 'man'
        elif a == 'member_ico':
            return 'woman'
    if data == None:
        for header, address, price, image1, image2, name, gender in zip(headers, addresses, prices, images1, images2, names, genders):
        data = {
            'header': header.get('header'),
            'address': address.get('adderss'),
            'price': price.get('price'),
            'image1': image1.get('image1'),
            'image2': images2.get('src'),
            'name': name.get('name'),
            'gender': crawl_gender(genders)
        }
            print(data)

 crawler('http://bj.xiaozhu.com/fangzi/1115060277.html')

以下是编译器返回的内容：

Traceback (most recent call last):
  File "/Users/duanshulan/PycharmProjects/untitled1/Crawler.py", line 36, in <module>
    crawler('http://bj.xiaozhu.com/fangzi/1115060277.html')
  File "/Users/duanshulan/PycharmProjects/untitled1/Crawler.py", line 30, in crawler
    'image2': images2.get('src'),
  AttributeError: 'list' object has no attribute 'get'

Answer 1

这意味着您的images2变量中有超过1张图片。尝试：

'image2': images2[0].get('src'),

仅访问第一个。