pip install requests

1 import requests
2 
3 url = ‘http://www.baidu.com‘
4 
5 response = requests.get(url).content.decode()
6 
7 print(response)

 1 import requests
 2 
 3 url = ‘http://www.baidu.com/s?‘
 4 
 5 headers = {
 6     "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36"
 7 }
 8 
 9 wd = {"wd":"中国"}
10 
11 response = requests.get(url,params=wd,headers=headers)
12 
13 data = response.text # 表示返回一个字符串形式数据
14 
15 data2 = response.content # 表示返回一个二进制形式数据
16 
17 print(data)

 1 import requests
 2 import re
 3 
 4 #构造请求头信息
 5 header={
 6 "User-Agent":"Mozilla/5.0 (Linux; U; An 7 droid 8.1.0; zh-cn; BLA-AL00 Build/HUAW 8 EIBLA-AL00) AppleWebKit/537.36 (KHTML, l 9 ike Gecko) Version/4.0 Chrome/57.0.2987.1310 2 MQQBrowser/8.9 Mobile Safari/537.36"
11 }
12 
13 url="http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"
14 
15 key="自学"
16 
17 #post请求需要提交的参数
18 formdata={
19    "i":key,
20    "from":"AUTO",
21    "to":"AUTO",
22    "smartresult":"dict",
23    "client":"fanyideskweb",
24    "salt":"15503049709404",
25    "sign":"3da914b136a37f75501f7f31b11e75fb",
26    "ts":"1550304970940",
27    "bv":"ab57a166e6a56368c9f95952de6192b5",
28    "doctype":"json",
29    "version":"2.1",
30    "keyfrom":"fanyi.web",
31    "action":"FY_BY_REALTIME",
32    "typoResult":"false"
33 }
34 
35 response = requests.post(url,headers=header,data=formdata)
36 
37 data = response.json()
38 
39 data2 = response.text
40 
41 data3 = response.content
42 
43 # 正则表达式，提取"tgt":"self-study"}]]}中间的变量
44 pat = r‘"tgt":"(.*?)"}]]}‘
45 
46 result = re.findall(pat,response.text)
47 
48 print(result)

 1 import requests
 2 
 3 # 设置ip地址
 4 # proxy = {"http":"http://代理IP地址：端口号"}
 5 proxy = {"http":"http://118.113.247.26:9999"}
 6 
 7 url = "http://www.baidu.com"
 8 
 9 response = requests.get(url,proxies=proxy)
10 
11 print(response)

 1 import requests
 2 
 3 url = ‘http://www.baidu.com‘
 4 
 5 response = requests.get(url)
 6 
 7 # 1、获取返回的cookiejar对象
 8 cookiejar = response.cookies
 9 
10 # 2、将cookiejar转换成字典
11 cookiedict = requests.utils.dict_from_cookiejar(cookiejar)
12 
13 print(cookiedict)

 1 import requests
 2 
 3 url = "http://www.renren.com/Plogin.do"
 4 
 5 header={
 6 "User-Agent":"Mozilla/5.0 (Linux; U; An 7 droid 8.1.0; zh-cn; BLA-AL00 Build/HUAW 8 EIBLA-AL00) AppleWebKit/537.36 (KHTML, l 9 ike Gecko) Version/4.0 Chrome/57.0.2987.1310 2 MQQBrowser/8.9 Mobile Safari/537.36"
11 }
12 
13 # 创建一个session对象
14 ses = requests.session()
15 
16 # 构造登录需要的参数
17 data={"email":"binzi_chen@126.com","password":"5tgb^YHN"}
18 
19 # 通过传递用户名密码得到cookie信息
20 ses.post(url,data=data)
21 
22 # 请求需要的页面
23 response = ses.get("http://www.renren.com/880151237/profile")
24 
25 print(response.text)

 1 import re # 引入正则表达式库
 2 import requests
 3 import time
 4 
 5 # http://www.htqyy.com/top/musicList/hot?pageIndex=1&pageSize=20 # 第一页
 6 # http://www.htqyy.com/top/musicList/hot?pageIndex=1&pageSize=20 # 第二页
 7 # http://www.htqyy.com/top/musicList/hot?pageIndex=2&pageSize=20 # 第三页
 8 
 9 # 页码-1
10 
11 # 歌曲url  http://www.htyy.com/play/20
12 # 播放资源 http://f2.htqyy.com/play8/11/mp3/8
13 
14 # page = int(input("请输入您要爬取的页数："))
15 
16 header = {
17     "Referer":"http://www.htqyy.com/top/hot"
18 }
19 
20 songID = []
21 songName = []
22 
23 for i in range(0,2):
24     url = "http://www.htqyy.com/top/musicList/hot?pageIndex="+ str(i)+"&pageSize=20"
25 
26     # 获取音乐榜单的网页信息
27     html = requests.get(url,headers=header)
28 
29     strr = html.text
30 
31     # print(strr)
32     # class ="title" > < a href="/play/33" target="play" title="清晨" sid="33" > 清晨 < / a > < / span >
33 
34     part1 = r‘title="(.*?)" sid‘
35     part2 = r‘sid="(.*?)"‘
36 
37 
38     idlist = re.findall(part2,strr)
39     titlelist = re.findall(part1,strr)
40 
41     songID.extend(idlist) # extend()把两个列表合成一个列表
42     songName.extend(titlelist)
43 
44 print("歌曲列表：",songName)
45 print("歌曲ID：",songID)
46 
47 for i in range(0,len(songID)):
48     songUrl = "http://f2.htqyy.com/play8/" + str(songID[i]) + "/mp3/8"
49     song = songName[i]
50 
51     data = requests.get(songUrl).content
52 
53     with open("D:\\Documents\\Music\\{}.mp3".format(song),"wb") as f:
54         f.write(data)
55     time.sleep(0.5)