|
#引用第三方库，re，requests库
import requests #用来提取
import re #用来正则
#对网页进行提取，把里面的信息提取出来
def html(url):
try:#看到headers别慌，这都是复制来的
headers = {
'authority': 'music.163.com',
'upgrade-insecure-requests': '1',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
'sec-fetch-dest': 'iframe',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'navigate',
'referer': 'https://music.163.com/',
'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
'cookie': '_ga=GA1.2.1412864897.1553836840; _iuqxldmzr_=32; _ntes_nnid=b757609ed6b0fea92825e343fb9dfd21,1568216071410; _ntes_nuid=b757609ed6b0fea92825e343fb9dfd21; WM_TID=Pg3EkygrDw1EBAVUVRIttkwA^%^2Bn1s1Vww; P_INFO=183605463^@qq.com^|1581593068^|0^|nmtp^|00^&99^|null^&null^&null^#not_found^&null^#10^#0^|^&0^|^|183605463^@qq.com; mail_psc_fingerprint=d87488b559a786de4942ad31e080b75f; __root_domain_v=.163.com; _qddaz=QD.n0p8sb.xdhbv8.k75rl6g4; __oc_uuid=2f4eb790-6da9-11ea-9922-b14d70d91022; hb_MA-BFF5-63705950A31C_source=blog.csdn.net; UM_distinctid=171142b7a6d3ba-0fbb0bf9a78375-4313f6a-144000-171142b7a6e30b; vinfo_n_f_l_n3=6d6e1214849bb357.1.0.1585181322988.0.1585181330388; JSESSIONID-WYYY=jJutWzFVWmDWzmt2vzgf6t5RgAaMOhSIKddpHG9mTIhK8fWqZndgocpo87cjYkMxKIlF^%^2BPjV^%^2F2NPykYHKUnMHkHRuErCNerHW6DtnD8HB09idBvHCJznNJRniCQ9XEl^%^2F7^%^2Bovbwgy7ihPO3oJIhM8s861d^%^2FNvyRTMDjVtCy^%^5CasJPKrAty^%^3A1585279750488; WM_NI=SnWfgd^%^2F5h0XFsqXxWEMl0vNVE8ZjZCzrxK^%^2F9A85boR^%^2BpV^%^2BA9J27jZCEbCqViaXw6If1Ecm7okWiL^%^2BKU2G8frpRB^%^2BRRDpz8RNJnagZdXn6KNVBHwK2tnvUL^%^2BxWQ^%^2BhGf2aeWE^%^3D; WM_NIKE=9ca17ae2e6ffcda170e2e6ee84b64f86878d87f04fe9bc8fa3c84f878f9eafb65ab59498cccf48f7929fb5e72af0fea7c3b92a91b29987e670edeba8d1db4eb1af9899d64f8fb40097cd5e87e8968bd949baaeb8acae3383e8fb83ee5ae9b09accc4338aeef98bd94987be8d92d563a388b9d7cc6ef39bad8eb665a989a7adaa4197ee89d9e57ab48e8eccd15a88b0b6d9d1468ab2af88d9709cb2faaccd5e8298b9acb180aeaa9badaa74958fe589c66ef2bfabb8c837e2a3; playerid=67583529',
}#看到headers别慌，这都是复制来的
res= requests.get(url, headers=headers)
res.encoding=res.apparent_encoding
res.raise_for_status()
return res.text
except:
print("网页提取出现问题")
#提取信息了
def tiqu(text):
try:
list = []# 提取文章中的所用信息，然后封装成一个列表，方便后续使用
all=re.findall(r'(.*?)',text,re.I)
str=all[0]
strlist=re.findall(r'">(.*?)',str)
print("排名\t\t\t歌名")
j=1
for i in strlist:
print("排名：{: |