导航

python用post请求网页

Posted on 2017-02-14 10:00  蓬莱诗人  阅读(283)  评论(0)    收藏  举报 
 1 # -*-coding:utf-8-*-
 2 from bs4 import BeautifulSoup
 3 import requests, time
 4 url =  'https://knewone.com/discover?page='
 5 
 6 def get_page(url, data=None):  # 获取页面
 7     wb_data = requests.get(url)
 8     soup = BeautifulSoup(wb_data.text, 'html.parser')
 9 
10     imgs = soup.select('a.cover-inner > img')
11     titles = soup.select('section.content > h4 >a')
12     links = soup.select('section.content > h4 > a')
13     # 数据打印
14     if data is None:
15         for img, title, link in zip(imgs, titles, links):
16             data = {
17                 'img': img.get('src'),
18                 'title': title.get('title'),
19                 'link': link.get('href')
20             }
21             print data
22 
23 def get_more_pages(start, end):
24     for one in range(start, end):
25         get_page(url + str(one))
26         time.sleep(2)   # 获取链接
27 
28 get_more_pages(1, 10)    # 调用函数
# -*-coding:utf-8-*-
from bs4 import BeautifulSoup
import requests, time
url =  'https://knewone.com/discover?page='

def get_page(url, data=None):  # 获取页面
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text, 'html.parser')

    imgs = soup.select('a.cover-inner > img')
    titles = soup.select('section.content > h4 >a')
    links = soup.select('section.content > h4 > a')
    # 数据打印
    if data is None:
        for img, title, link in zip(imgs, titles, links):
            data = {
                'img': img.get('src'),
                'title': title.get('title'),
                'link': link.get('href')
            }
            print data

def get_more_pages(start, end):
    for one in range(start, end):
        get_page(url + str(one))
        time.sleep(2)   # 获取链接

get_more_pages(1, 10)    # 调用函数

　　
Poem code