这次运用数据来存储,并从中提取数据
成果展示
部分成果1.png
部分成果2.png
代码
import requests
import time
from bs4 import BeautifulSoup
from pymongo import MongoClient
client = MongoClient('localhost', 27017)
PhoneNum = client['PhoneNum']
url_list = PhoneNum['url_list']
phone_info = PhoneNum['phone_info']]
# spider 1
def get_phone_link(pages):
url = 'http://bj.58.com/shoujihao/pn{}/'.format(str(pages))
wb_data = requests.get(url)
time.sleep(1)
soup = BeautifulSoup(wb_data.text, 'lxml')
links = soup.select('li a.t')
numbers = soup.select('strong')
lk = soup.select('#infocont > span > b'