python爬虫 学习 京东页面、亚马逊访问|、百度搜索、网上爬取图片 DAY2

import requests
def getHTMLText(url):
    try:
        r = requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text[:500]
    except:
        print("产生异常")

if __name__=="__main__":
    url = "https://item.jd.com/4483108.html"
    print(getHTMLText(url))
    

import requests
url = "https://www.icourse163.org/learn/BIT-1001870001?tid=1002781006#/learn/content?type=detail&id=1003983061&cid=1004883298"
try:
    kv = {'user-agent':'Mozilla/5.0'}
    r = requests.get(url,headers=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print("爬取失败")

import requests
url = "http://www.baidu.com/s"
keyword ="python"
try:
    kv = {'wd':keyword}
    r = requests.get(url,params=kv)
    print(r.request.url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(len(r.text))
except:
    print("爬取失败")

 

import requests
import os
url = "http://bbs.fengniao.com/forum/pic/123456.jpg"
root="D://pic//"
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)
        f = open(path,'wb')
        f.write(r.content)
        f.close()
        print("文件保存成功")
    else:
        print("文件已存在")
except:
        print("爬取失败")