python - BeautifulSoup 没有获取所有数据，仅获取部分数据

Question

import requests
from bs4 import BeautifulSoup


def trade_spider(max_pages):
page = 0
while page <= max_pages:
    url = 'http://orangecounty.craigslist.org/search/foa?s=' + str(page * 100)
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text)
    for link in soup.findAll('a', {'class':'hdrlnk'}):
        href = 'http://orangecounty.craigslist.org/' + link.get('href')
        title = link.string
        print title
        #print href
        get_single_item_data(href)
    page += 1

def get_single_item_data(item_url):
    source_code = requests.get(item_url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text)
    for item_name in soup.findAll('section', {'id':'postingbody'}):
        print item_name.string



trade_spider(1)

我正在尝试抓取 craigslist(用于练习)，http://orangecounty.craigslist.org/search/foa?s=0尤其。我现在将其设置为打印条目的标题和条目的描述。问题是，虽然列出的每个对象的标题都正确打印，但大多数对象的描述都被列为“无”，即使有明确的描述。任何帮助，将不胜感激。谢谢。

Answer 1

你就快到了。只需将 item_name.string 更改为 item_name.text