import request
from bs4 import BeautifulSoup
def getHTMLText(url):
try:
proxy={'https':'http://182.34.33.44:9999'}
hd={'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'}
r=requests.request('GET',url,proxies=proxy,headers=hd,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
print("getHTMLText!!!")
def filluList(uList,Text):
try:
soup=Beautiful(Text,'html.parser')
name=soup.find('span',id='h-name').string
gender=soup.find('span',id='h-gender').attrs['class'].string
level=soup.find_all('div').attrs['class'].children[2].attr['lvl'].string
fs=soup.find('p',id='n-fs').string
bf=soup.find('p',id='n-bf').string
ulist.append([name,gender,fs,bf])
except:
print("filluList!!!")
def printulist(uList,num):
try:
output='{0:^10}\t{1:{3}^10}\t{2:^10}\t{2:^10}\t{2:^10}' # 優化輸出
print(output.format("昵稱","性別","級別","粉絲","播放",chr(12288)))
for u in range(num):
u1=uList[u]
print(output.format(u1[0],u1[1],u1[2],u1[3],ul[4],chr(12288)))
except:
print("printulist!!!")
if __name__=='__main__':
uList=[]
start_num=454222
num=20
start_url='https://space.bilibili.com/'
for n in range(start_num,start_num+num):
try:
url=start_url+str(n)
print(url)
Text=getHTMLText(url)
filluList(uList,Text)
except:
continue
printulist(uList,num)
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/147597.html
上一篇：流量轉發映射
下一篇：求助，這道題不會