爬“当当网”的图书

luoyunjian

"""
1、分析网站结构

"""
import requests
import csv
from bs4 import BeautifulSoup

url =  'http://search.dangdang.com/?key=%C8%FD%C4%EA%BC%B6%BF%CE%CD%E2%D4%C4%B6%C1%B1%D8%B6%C1%CA%E9&act=input'

# 1>获取网络返回的html数据

def get_requests_data(url):
    req = requests.get(url).text
    return req

#2>数据的解析  
def parser_content(content):
    soup = BeautifulSoup(content,'lxml')
    books = soup.findall('a',class_ = 'pic')
    print(books)
   
#3>数据的保存
    with open(fileName,'a+',encoding = 'utf_8') as file:
        file_names = ['书名','页面地址','图片地址']
        writer = csv.DictWriter(file,file_names)
        
        for book in books:
            print(list(book.children)[0].attrs)
            if len(list(book.children)[0].attrs) == 3:
                img = list(book.children)[0].attrs['data-original']
            else:
                img = list(book.children)[0].attrs['src']
            row = {file_names[0]:book.attrs['title'],
                   file_names[1]:book.attrs[''],
                   file_names[2]:book.attrs['']
            }
#if _main_ == '_main_':
fileName = 'dd_book.csv'
req = get_requests_data(url)
parser_content(req)