前言
本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理。
一个简单的Python资讯采集案例，列表页到详情页，到数据保存，保存为txt文档，网站网页结构算是比较规整，简单清晰明了，资讯新闻内容的采集和保存！
应用到的库
requests，time，re，UserAgent，etree
import requests,time,re
from fake_useragent import UserAgent
from lxml import etree列表页面
列表页，链接xpath解析
href_list=req.xpath('//ul[@class="news-list"]/li/a/@href')详情页
内容xpath解析
h2=req.xpath('//div[@class="title-box"]/h2/text()')[0]
author=req.xpath('//div[@class="title-box"]/span[@class="news-from"]/text()')[0]
details=req.xpath('//div[@class="content-l detail"]/p/text()')内容格式化处理
detail='\n'.join(details)标题格式化处理，替换非法字符
pattern = r"[\/\\\:\*\?\"\<\>\|]"
new_title = re.sub(pattern, "_", title) # 替换为下划线保存数据，保存为txt文本
def save(self,h2, author, detail):
with open(f'{h2}.txt','w',encoding='utf-8') as f:
f.write('%s%s%s%s%s'%(h2,'\n',detail,'\n',author))
print(f"保存{h2}.txt文本成功！")遍历数据采集，yield处理
def get_tasks(self):
data_list = self.parse_home_list(self.url)
for item in data_list:
yield item程序运行效果
程序采集效果
附源码参考：
#研招网考研资讯采集
#20200710 by微信：huguo00289
# -*- coding: UTF-8 -*-
import requests,time,re
from fake_useragent import UserAgent
from lxml import etree
class RandomHeaders(object):
ua=UserAgent()
@property
def random_headers(self):
return {
'User-Agent': self.ua.random,
}
class Spider(RandomHeaders):
def __init__(self,url):
self.url=url
def parse_home_list(self,url):
response=requests.get(url,headers=self.random_headers).content.decode('utf-8')
req=etree.HTML(response)
href_list=req.xpath('//ul[@class="news-list"]/li/a/@href')
print(href_list)
for href in href_list:
item = self.parse_detail(f'https://yz.chsi.com.cn{href}')
yield item
def parse_detail(self,url):
print(f">>正在爬取{url}")
try:
response = requests.get(url, headers=self.random_headers).content.decode('utf-8')
time.sleep(2)
except Exception as e:
print(e.args)
self.parse_detail(url)
else:
req = etree.HTML(response)
try:
h2=req.xpath('//div[@class="title-box"]/h2/text()')[0]
h2=self.validate_title(h2)
author=req.xpath('//div[@class="title-box"]/span[@class="news-from"]/text()')[0]
details=req.xpath('//div[@class="content-l detail"]/p/text()')
detail='\n'.join(details)
print(h2, author, detail)
self.save(h2, author, detail)
return h2, author, detail
except IndexError:
print(">>>采集出错需延时，5s后重试..")
time.sleep(5)
self.parse_detail(url)
@staticmethod
def validate_title(title):
pattern = r"[\/\\\:\*\?\"\<\>\|]"
new_title = re.sub(pattern, "_", title) # 替换为下划线
return new_title
def save(self,h2, author, detail):
with open(f'{h2}.txt','w',encoding='utf-8') as f:
f.write('%s%s%s%s%s'%(h2,'\n',detail,'\n',author))
print(f"保存{h2}.txt文本成功！")
def get_tasks(self):
data_list = self.parse_home_list(self.url)
for item in data_list:
yield item
if __name__=="__main__":
url="https://yz.chsi.com.cn/kyzx/jyxd/"
spider=Spider(url)
for data in spider.get_tasks():
print(data)