Python爬取网页全代码

Posted 2020-11-05 zhenshj

#爬取京东全代码

import requests
url = "http://item.jd.com/2967929.html"
try:
    r = requests.get(url)
    r.raise_for_status() #在返回200不产生异常，否则会产生异常
    r.encoding = r.apparent_encoding
    print(r.text[:10000])
except:
    print("爬取失败")

#爬取亚马逊全代码
import requests
url = "https://www.amazon.cn/gp/product/B01M8L5Z3Y"
try:
    kv = {‘user-agent‘:‘Mozilla/5.0‘}
    r = requests.get(url,headers=kv)
    r.raise_for_status() #在返回200不产生异常，否则会产生异常
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print("爬取失败")

#爬取百度搜索全代码
import requests
keyword = "Python"
try:
    kv = {‘wd‘:keyword}
    r = requests.get("http://www.baidu.com/s",params=kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬取失败")

#爬取360搜索全代码
import requests
keyword = "Python"
try:
    kv = {‘q‘:keyword}
    r = requests.get("http://www.so.com/s",params=kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬取失败")