import urllib.request
import re # 內庫 標準庫
import json
from bs4 import beautifulsoup
#url**
index_url = ''
html = urllib.request.urlopen(index_url)
bsobj = beautifulsoup(html,"html.parser")
namelist = bsobj.findall("a",)
'''num_people = bsobj.findall("span",)
num_barrage = bsobj.findall("span",)
time_up = bsobj.findall("span",)
'''up_name = bsobj.findall("a",)
'''for num in num_people:
print(name.get_text())
for num in num_barrage:
print(name.get_text())
for time in time_up:
print(name.get_text())
'''for time in up_name:
print(time)
# 3.儲存資料 資料持久化
#處理每乙個資料
goods_info1 =
for name in namelist:
temp1 =
print(goods_info1)
goods_info2 =
for name in up_name:
temp2 =
print(goods_info2)
fb = open('bilibili爬蟲結果.csv','w',encoding= 'utf-8')
#寫表頭
fb.write('課程名稱,課程**,up主,up主個人空間\n')
#乙個商品一行資料
for item in goods_info1:
temp1=',\n'.format(**item)
fb.write(temp1)
for item in goods_info2:
temp2=',\n'.format(**item)
fb.write(temp2)
fb.close()
有點小問題，但是沒改正。。。。
爬了一下b站，，只爬了一頁，後續的等等再寫吧，畢竟副業。。。。。。
乙個賊簡單的python爬蟲例項
這真的是乙個很簡單地python爬蟲，但是我卻做到現在了，哎 爬蟲的所有學習都來自於b站 up豬luvm的小屋 import requests import json import os header class douban def init self,url,dir self.url url s...
寫了乙個新浪部落格的爬蟲
語言 c 用到的第三方庫 軟體介面 由於原理非常簡單,花了乙個小時寫了一下,直接上 using system using system.io using system.net using system.text using system.text.regularexpressions using s...
寫了個簡單的內聯API鉤子類
class capihook bool initial lpvoid lpoldprocaddr,lpvoid lpnewprocaddr m lpoldprocaddr lpoldprocaddr m lpnewprocaddr lpnewprocaddr ifdef win64 m szjmpc...