python3抓取php,python3 实现 抓取 糗事百科 的内容

# 抓取糗事百科的内容

import requests

from lxml import etree

class Qiushi() :

def __init__(self) :

self.url = 'http://www.qiushibaike.com/8hr/page/{}';

self.headers = {

"User-Agent":"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1 Trident/5.0;"

};

def parse_url(self , url) :

response = requests.get(url , timeout = 10 , headers = self.headers)

assert response.status_code == 200

print(url)

return etree.HTML(response.text)

def parse_content(self , html) :

item = html.xpath('//div[@class="recommend-article"]/ul/li')

print(item)

for i in item :

# 内容

print(i.xpath('./div/a[@class="recmd-content"]/text()'));

# 好笑数

print(i.xpath('./div/div[@class="recmd-detail clearfix"]/div/span[1]/text()'))

# 评论数

print(i.xpath('./div/div[@class="recmd-detail clearfix"]/div/span[4]/text()'))

# 用户名

print(i.xpath('./div/div[@class="recmd-detail clearfix"]/a/span/text()'))

# 头像地址

print(i.xpath('./div/div[@class="recmd-detail clearfix"]/a/img/@src'))

def run(self) :

url = self.url.format(1);

html = self.parse_url(url);

self.parse_content(html);

if __name__ == '__main__':

qiu = Qiushi();

qiu.run();