代码拉取完成,页面将自动刷新
# https://www.icourse163.org/learn/BIT-1001870001?tid=1206093223#/learn/content
# -*- coding: utf-8 -*-
# import scrapy
# class DemoSpider(scrapy.Spider):
# name = "demo"
# #allowed_domains = ["python123.io"]
# start_urls = ['https://python123.io/ws/demo.html']
# def parse(self, response):
# fname = response.url.split('/')[-1]
# with open(fname, 'wb') as f:
# f.write(response.body)
# self.log('Saved file %s.' % name)
import requests
# url = "https://item.jd.com/2967929.html"
# try:
# r = requests .get(url)
# r.raise_for_status()
# r.encoding = r.apparent_encoding
# print(r. text[: 1000])
# except:
# print("爬取失敗")
# url = "https://www.amazon.cn/gp/product/B01M8L5Z3Y"
# try:
# # 通过修改headers的键值对,来模拟浏览器 Mozilla
# kv = {'user-agent': 'Mozilla/5.0'}
# r = requests .get(url, headers=kv)
# print(r.request.headers)
# r.raise_for_status()
# print(r.encoding)
# r.encoding = r.apparent_encoding
# print(r.encoding)
# print(r. text[1000: 2000])
# except:
# print("爬取失敗")
# # 要搜索的关键词 keyword
# keyword = "Python"
# url = "http://www.baidu.com/s"
# try:
# kv = {'wd': keyword}
# r = requests .get(url, headers=kv)
# print(r.request.url)
# r.raise_for_status()
# print(len(r. text))
# except:
# print("爬取失敗")
#
# # 要搜索的关键词 keyword
# keyword = "Python"
# url = "http://www.so.com/s"
# try:
# kv = {'q': keyword}
# r = requests .get(url, params=kv)
# print(r.request.url)
# r.raise_for_status()
# print(len(r. text))
# except:
# print("爬取失敗")
# import os
# url = "http://image.nationalgeographic.com.cn/2017/0211/20170211061910157.jpg"
# root = "E://pics//"
# path = root + url.split('/')[-1]
# try:
# if not os.path.exists(root):
# os.mkdir(root)
# if not os.path.exists(path):
# r = requests.get(url)
# with open(path, 'wb') as f:
# f.write(r.content)
# f.close()
# print("文件保存成功")
# else:
# print("文件已经存在")
# except:
# print("爬取失敗")
# IP查询
# url = "http://m.ip138.com/ip.asp?ip="
# try:
# r = requests.get(url+'202.204.80.112')
# r.raise_for_status()
# r.encoding = r.apparent_encoding
# print(r. text[-500:])
# except:
# print("爬取失敗")
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。