内涵段子脑筋急转弯(mongodb)
1.网址: www.neihan8.com
2.步骤
1.找URL规律
第1页: https://www.neihan8.com/njjzw/
第2页: https://www.neihan8.com/njjzw/index_2.html
2.写正则
‘< div class=“text-column. * ?title=”(.*?)">. * ?< div class=“desc”>(. * ?)< /div>’,re.S
3.写代码
import requests
import re
import pymongo
class NeihanSpider(object):
def __init__(self):
self.baseurl = 'https://www.neihan8.com/njjzw/'
self.headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50'}
self.proxies = {}
self.conn = pymongo.MongoClient('数据库地址',27017)
self.db = self.conn['neihandb']
self.myset = self.db['njjzw']
# 获取页面
def getPage(self,url):
res = requests.get(url,proxies=self.proxies,headers=self.headers)
res.encoding = 'utf-8'
html = res.text
self.parsePage(html)
# 解析页面
def parsePage(self,html):
p = re.compile('<div class="text-column.*?title="(.*?)">.*?<div class="desc">(.*?)</div>',re.S)
rList = p.findall(html)
self.writeMongo(rList)
# 保存到mongodb
def writeMongo(self,rList):
for r in rList:
d = {
'question':r[0].strip(),
'answer':r[1].strip()
}
self.myset.insert_one(d)
# 主函数
def workOn(self):
self.getPage(self.baseurl)
print('第1页爬取成功')
for pg in range(2,n+1):
# 拼接URL
url = self.baseurl + 'index_' + str(pg) + '.html'
self.getPage(url)
print('第%d页爬取成功' % pg)
if __name__ == '__main__':
spider = NeihanSpider()
spider.workOn()