Python抓取某平台代码

最新推荐文章于 2025-09-08 10:18:06 发布

原创最新推荐文章于 2025-09-08 10:18:06 发布 · 292 阅读

0 ·

CC 4.0 BY-SA版权

Python 专栏收录该内容

22 篇文章

订阅专栏

本文介绍了一个使用Python进行网络爬取的实例，通过定义特定的URL模板和日期范围，该脚本能够从指定市场ID获取季度性的网页数据。利用Requests库进行HTTP请求，并采用简单的缓存机制来提高效率。

#!/usr/bin/python
# -*- coding: GBK -*-

import os, sys, time
import requests
import arrow
import hashlib
from unipath import Path

def file_get_contents( url):
    s = requests.Session()
    headers={
      "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
      "Accept-Encoding": "gzip, deflate, br",
      "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
      "Connection":"keep-alive",
      "Upgrade-Insecure-Requests":"1",
      "User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:55.0) Gecko/20100101 Firefox/55.0"
    }

    r = s.get( url, timeout=10,headers=headers)
    r.encoding = 'gbk'
    return r.text

def by_market( market_id):
    page = 1
    page_count = 1;
    url_template = ''
    for start in arrow.Arrow.range('quarter', arrow.get('2014-01-01','YYYY-MM-DD'), arrow.now()):
        url = url_template.format( **{ 'market_id':market_id, 'start_time': start.format("YYYY-MM-DD"), 'end_time':start.shift( months=3).format("YYYY-MM-DD"),'page': page})
        Item( url)
        
        


class Item:
    url = ''
    content = ''
    
    def __init__( self, url):
        self.url = url
        self.content = self.get_contents( url)
        print( self.content)
    def get_contents( self, url):
        cache = Path('./cache/'+hashlib.md5( url.encode(encoding='GBK')).hexdigest())
        if cache.exists():
            content = cache.read_file()
        else:
            content = file_get_contents( url)
            cache.write_file( content)
            time.sleep(1)
        
        return content;
#print( file_get_contents( url))
by_market( 2604461)