获取哔哩哔哩网站的排行榜

 

      爬取下边五个榜单

# 用requests模块做请求，页面通过etree类将html字符串转化为Element对象，以便我们使用xpath解析页面（requests,etree,xpath）

import requests
from lxml import etree

def bilibili(str):
html=requests.get(str).text
doc=etree.HTML(html)
result=doc.xpath('//div[@class="info"]/a/text()')
x=0
for results in result:
# 计数
x=x+1
print(results)
print(x)

# 全站榜
bilibili('https://www.bilibili.com/ranking/all/0/0/3')
#原创榜
bilibili('https://www.bilibili.com/ranking/origin/0/0/3')
#新番榜
bilibili('https://www.bilibili.com/ranking/bangumi/13/0/3')
#影视榜
bilibili('https://www.bilibili.com/ranking/cinema/177/0/3')
#新人榜
bilibili('https://www.bilibili.com/ranking/rookie/0/0/3')