2-1homework

结果

---

Result.png

我的代码

---

from bs4 import BeautifulSoup
import requests
import time
import pymongo

__author__ = 'CP6'

client = pymongo.MongoClient('localhost', 27017)
xiaozhuDB = client['xiaozhuDB']
xiaozhuTb = xiaozhuDB['xiaozhuTb']

urls = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i)) for i in range(1, 4)]

def somMethod():
    for single_url in urls:
        wb_data = requests.get(single_url)
        soup = BeautifulSoup(wb_data.text, 'lxml')
        time.sleep(2)
        titles = soup.select('span.result_title')
        prices = soup.select('span.result_price > i')
        links = soup.select('#page_list > ul > li > a')

        # print(titles, prices, links,sep="\n-------------------------\n")
        # info = []
        for title, price, link in zip(titles, prices, links):
            data = {
                'title': title.get_text(),
                'price': int(price.get_text()),
                'link': link.get('href')
            }
            # print(data)
            # info.append(data)
            xiaozhuTb.insert_one(data)
        # for item in info:
        #     # print(item)
        #     if item['price'] >= 500:
        #         print(item)


def getResult():
    for item in xiaozhuTb.find({'price': {'$gt': 500}}):
        print(item)

if __name__ == '__main__':
    somMethod()
    getResult()

总结

---

• 1. 数据库查询方法

# $lt/$lte/$gt/$gte/$ne 等价于 less than/equal/greater/not

• 2. 打开文件，读取内容

path = 'C:\\Users\Queen\Desktop\MuggleCode\Mycode\week2\\2-1\\2-1code_video\walden.txt'

with open(path, 'r') as f:
    lines = f.readlines() // 读取文件的每一行
    for index, line in enumerate(lines):
        data = {
            'index': index,
            'line': line,
            'words': len(line.split())
        }
        print(data)

• 3. enumerate 函数： 用于遍历序列中的元素以及它们的下标

for i,j in enumerate(('a','b','c')):
     print i,j
 
0 a
1 b
2 c

• 4. 数据库操作步骤

// 建立连接
client = pymongo.MongoClient('localhost', 27017)
// 创建DB
xiaozhuDB = client['xiaozhuDB']
// 创建Table
xiaozhuTb = xiaozhuDB['xiaozhuTb']
// 插入数据
xiaozhuTb.insert_one(data)
// 查询数据
for item in xiaozhuTb.find({'price': {'$gt': 500}}):
        print(item)

• 5. Bs4 prettify

print(soup.b.prettify()) // html以标准格式输出