欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

Python爬虫实践~BeautifulSoup+urllib+Flask实现静态网页的爬取

程序员文章站 2022-05-03 20:03:21
...

爬取的网站类型:

    论坛类网站类型

涉及主要的第三方模块:

    BeautifulSoup:解析、遍历页面

    urllib:处理URL请求

    Flask:简易的WEB框架

介绍:

        本次主要使用urllib获取网页数据,然后通过BeautifulSoup进行页面解析,返回json结构的数据。

功能点:

  • urllib根据URL通过GET方式获取网页内容;

  • 通过JSON文件配置

  • 解析页面结构,返回JSON结构的数据

  • 提供REST服务进行调用

     

特点:

1、提供数据描述服务,总页面,每页条数,总条数;

2、增量请求数据,只获取当前时间和上次请求时间之间的数据;

3、控制请求时间间隔,防治IP被封杀

4、分页数据请求

5、修改请求关键字,并记录上次的请求关键字

 

主要代码结构:

- 公共请求端封装

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
from urllib import request
from urllib.parse import quote
import string
import requests

# 静态页面基类
class StaticBase():
    # 获取网页内容
    def __getHTMLText(self,url,code="utf-8"):
        try:
            r = requests.get(url)
            r.raise_for_status()
            r.encoding = code
            return r.text
        except:
            return ""
    # get方式请求数据
    def getUrl(self,url,code='utf-8'):
        url = quote(url,safe=string.printable)
        req = request.Request(url)
        req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36')
        with request.urlopen(req) as f:
            print('Status:',f.status,f.reason)
            return f.read().decode(code)

#s = StaticBase()
#print(s.getUrl('http://www.baidu.com/','utf-8'))

- 配置文件

{
   "host": "http://shangyu.108sq.cn", 
   "base_url": "http://shangyu.108sq.cn/shuo/search?sertype=4", 
   "key_words": "污染", 
   "page_size": 30, 
   "search_key": "", 
   "last_request_time": 1562142204.149511, 
   "request_gap": 60
  }

- 解析服务

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup
from datetime import datetime
import json
from common.staticBase import StaticBase

class Shangyh108(StaticBase):

    __config_file = "config.json"   #配置文件
    __text = ""                     #解析的网页内容
    __config_dict = {}              #配置集合
    __url = ""                      #请求的URL
    __keywords = ""                 #关键字
    __last_request_time = 0         #上次请求时间
    # 构造函数
    def __init__(self):
        self.__config_dict = self.__getConfig()
        # 查询关键字
        if len(self.__config_dict['search_key']) >0 :
            self.__keywords = self.__config_dict['search_key']
        else:
            self.__keywords = self.__config_dict['key_words']
        self.__url = self.__getUrl()
    # 获取网页内容
    def getText(self):
        print(self.__url)
        self.__text = StaticBase.getUrl(self,self.__url)

    # 获取第一页内容
    def getFirstPageText(self,url=''):
        if self.checkRquestTime():
            if len(url)==0 :
                url = self.__getUrl()
            self.__text = StaticBase.getUrl(self,url)
            return self.parseHTML()
        else:
            print("操作频繁请稍后重新")
    # 获取下一页
    def getNextPage(self,url):
        url = self.__config_dict['host']+url
        print(url)
        self.__text = StaticBase.getUrl(self,url)
        return self.parseHTML()

    # 为防止请求对服务器造成太大压力,控制请求的时间间隔,最少为5分钟
    def checkRquestTime(self):
        request_gap = self.__config_dict['request_gap']
        last_request_time = self.__config_dict['last_request_time']
        dt_now = datetime.now().timestamp()
        self.__last_request_time = last_request_time  # 记录上次请求的时间,为了获取阶段性的数据
        if last_request_time == 0:  #第一次请求,直接通过
            last_request_time = dt_now
        elif last_request_time+request_gap > dt_now:
            print("请求过度频繁,请稍后重试")
            return False
        else:
            last_request_time = dt_now

        self.__setConfig('last_request_time',last_request_time)
        return True

    # 获取网页描述信息
    def getDesc(self):
        self.getText()
        soup = BeautifulSoup(self.__text,'html.parser')
        obj_count = soup.select('.count')[0]
        count_str = str(obj_count.string).replace("(共","").replace("条)","")
        count = int(count_str)
        pageSize = int(self.__config_dict['page_size'])
        host = self.__config_dict['host']
        if count % pageSize == 0 :
            pages = count//pageSize
        else:
            pages = count // pageSize + 1
        desc = {}
        desc['host'] = host
        desc['count'] = count
        desc['page_size'] = pageSize
        desc['total_page'] = pages
        # 增加分页的URL
        if pages > 0 :
            pageUrls = soup.select(".TCPage__middle > a")
            page_url = []
            for i in range(len(pageUrls)-1) :
                tag = pageUrls[i+1]
                page_url.append(tag['href'])
            desc['page_url'] = page_url
        return json.dumps(desc,ensure_ascii=False)

    # 解析网页内容
    def parseHTML(self):
        soup = BeautifulSoup(self.__text, 'html.parser')
        list_li = soup.select('.TCSayList .TCSayList_li')
        data_list = []
        for i in range(len(list_li)):
            item = {}
            temp = list_li[i]
            publish_time = temp.select('.TCSayList_li_time')[0]
            int_dt = int(publish_time['data-time'])

            if self.__last_request_time == 0 or self.__last_request_time < int_dt :
                # 发布时间
                item['publish_time_long'] = publish_time['data-time']
                item['publish_time_str'] = datetime.fromtimestamp(int(publish_time['data-time'])).strftime(
                    '%Y-%m-%d %H:%M:%S')

                # 数据标签
                item['data-tag'] = temp['data-tag']
                # 用户
                author = temp.select('.TCSayList_li_author')[0]
                item['author_name'] = author.string
                item['author_url'] = author['href']

                # 标题
                if len(temp.select('.TCSayList__title a')) >0:
                    title = temp.select('.TCSayList__title a')[0]
                    item['title'] = title.string
                    item['link_url'] = title['href']
                # 内容
                item['content'] = temp.select('.TCSayList_li_content')[0]['data-short']

                data_list.append(item)
        return data_list
    # 获取请求配置信息
    def __getConfig(self):
        with open(self.__config_file, "r",encoding="utf-8") as load_f:
            load_dict = json.load(load_f)
        return load_dict
    # 设置配置项
    def __setConfig(self,key,value):
        self.__config_dict[key] = value
        print(self.__config_dict)
        with open(self.__config_file,'w',encoding="utf-8") as f:
            f.write(json.dumps(self.__config_dict,ensure_ascii=False))

    def getKeywords(self):
        self.__keywords = input("请输入查询的关键字,多个关键字用“+”连接,默认关键字:环保+污染+投诉,使用默认关键字可直接按Enter:")
        if len(self.__keywords) == 0:
            self.__keywords = self.__config_dict['key_words']
        else:
            self.__setConfig("search_key",self.__keywords)

    # 获取请求的URL
    def __getUrl(self):
        base_url = self.__config_dict['base_url']
        # 组装查询参数
        url = base_url + "&key=" + self.__keywords
        return url

- REST服务端(目前服务没有暴露很多,但相应服务实现都已经实现)

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
from flask import Flask,jsonify,abort,request
from changshuo108.shangyu.Shangyh108 import Shangyh108

app = Flask(__name__)
# 支持中文
app.config['JSON_AS_ASCII'] = False
shangyue = Shangyh108()
@app.route('/shangyu108/api/desc',methods=['GET'])
def get_desc():
    return shangyue.getDesc()

@app.route('/shangyu108/api/first_page',methods=['GET'])
def get_firstPage():
    return jsonify({'data':shangyue.getFirstPageText('')})

@app.route('/shangyu108/api/page',methods=['POST'])
def get_article():
   if not request.json or not 'url' in request.json:
      abort(400)
   print(request.json['url'])
   return jsonify({'data':shangyue.getNextPage(request.json['url'])})

if __name__ == '__main__':
    app.run(debug=True)

 

爬取的网站类型:

    论坛类网站类型

涉及主要的第三方模块:

    BeautifulSoup:解析、遍历页面

    urllib:处理URL请求

    Flask:简易的WEB框架

介绍:

        本次主要使用urllib获取网页数据,然后通过BeautifulSoup进行页面解析,返回json结构的数据。

功能点:

  • urllib根据URL通过GET方式获取网页内容;

  • 通过JSON文件配置

  • 解析页面结构,返回JSON结构的数据

  • 提供REST服务进行调用

     

特点:

1、提供数据描述服务,总页面,每页条数,总条数;

2、增量请求数据,只获取当前时间和上次请求时间之间的数据;

3、控制请求时间间隔,防治IP被封杀

4、分页数据请求

5、修改请求关键字,并记录上次的请求关键字

 

主要代码结构:

- 公共请求端封装

#!/usr/bin/env python # -*- coding:utf-8 -*-from urllib import requestfrom urllib.parse import quoteimport stringimport requests
# 静态页面基类class StaticBase():    # 获取网页内容   使用的requests 库实现 def __getHTMLText(self,url,code="utf-8"): try: r = requests.get(url) r.raise_for_status() r.encoding = code return r.text except: return ""    # get方式请求数据  通过urllib记性实现GET请求 def getUrl(self,url,code='utf-8'): url = quote(url,safe=string.printable) req = request.Request(url) req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36') with request.urlopen(req) as f: print('Status:',f.status,f.reason) return f.read().decode(code)
#s = StaticBase()#print(s.getUrl('http://www.baidu.com/','utf-8'))

- 配置文件

{   "host": "http://shangyu.108sq.cn",    "base_url""http://shangyu.108sq.cn/shuo/search?sertype=4"   "key_words""污染"   "page_size"30   "search_key"""   "last_request_time"1562142204.149511   "request_gap"60  } 

- 解析服务

#!/usr/bin/env python # -*- coding:utf-8 -*-from bs4 import BeautifulSoupfrom datetime import datetimeimport jsonfrom common.staticBase import StaticBase
class Shangyh108(StaticBase):
__config_file = "config.json" #配置文件 __text = "" #解析的网页内容 __config_dict = {} #配置集合 __url = "" #请求的URL __keywords = "" #关键字 __last_request_time = 0 #上次请求时间 # 构造函数 def __init__(self): self.__config_dict = self.__getConfig() # 查询关键字 if len(self.__config_dict['search_key']) >0 : self.__keywords = self.__config_dict['search_key'] else: self.__keywords = self.__config_dict['key_words'] self.__url = self.__getUrl() # 获取网页内容 def getText(self): print(self.__url) self.__text = StaticBase.getUrl(self,self.__url)
# 获取第一页内容 def getFirstPageText(self,url=''): if self.checkRquestTime(): if len(url)==0 : url = self.__getUrl() self.__text = StaticBase.getUrl(self,url) return self.parseHTML() else: print("操作频繁请稍后重新") # 获取下一页 def getNextPage(self,url): url = self.__config_dict['host']+url print(url) self.__text = StaticBase.getUrl(self,url) return self.parseHTML()
# 为防止请求对服务器造成太大压力,控制请求的时间间隔,最少为5分钟 def checkRquestTime(self): request_gap = self.__config_dict['request_gap'] last_request_time = self.__config_dict['last_request_time'] dt_now = datetime.now().timestamp() self.__last_request_time = last_request_time # 记录上次请求的时间,为了获取阶段性的数据 if last_request_time == 0: #第一次请求,直接通过 last_request_time = dt_now elif last_request_time+request_gap > dt_now: print("请求过度频繁,请稍后重试") return False else: last_request_time = dt_now
self.__setConfig('last_request_time',last_request_time) return True
# 获取网页描述信息 def getDesc(self): self.getText() soup = BeautifulSoup(self.__text,'html.parser') obj_count = soup.select('.count')[0] count_str = str(obj_count.string).replace("(共","").replace("条)","") count = int(count_str) pageSize = int(self.__config_dict['page_size']) host = self.__config_dict['host'] if count % pageSize == 0 : pages = count//pageSize else: pages = count // pageSize + 1 desc = {} desc['host'] = host desc['count'] = count desc['page_size'] = pageSize desc['total_page'] = pages # 增加分页的URL if pages > 0 : pageUrls = soup.select(".TCPage__middle > a") page_url = [] for i in range(len(pageUrls)-1) : tag = pageUrls[i+1] page_url.append(tag['href']) desc['page_url'] = page_url return json.dumps(desc,ensure_ascii=False)
# 解析网页内容 def parseHTML(self): soup = BeautifulSoup(self.__text, 'html.parser') list_li = soup.select('.TCSayList .TCSayList_li') data_list = [] for i in range(len(list_li)): item = {} temp = list_li[i] publish_time = temp.select('.TCSayList_li_time')[0] int_dt = int(publish_time['data-time'])
if self.__last_request_time == 0 or self.__last_request_time < int_dt : # 发布时间 item['publish_time_long'] = publish_time['data-time'] item['publish_time_str'] = datetime.fromtimestamp(int(publish_time['data-time'])).strftime( '%Y-%m-%d %H:%M:%S')
# 数据标签 item['data-tag'] = temp['data-tag'] # 用户 author = temp.select('.TCSayList_li_author')[0] item['author_name'] = author.string item['author_url'] = author['href']
# 标题 if len(temp.select('.TCSayList__title a')) >0: title = temp.select('.TCSayList__title a')[0] item['title'] = title.string item['link_url'] = title['href'] # 内容 item['content'] = temp.select('.TCSayList_li_content')[0]['data-short']
data_list.append(item) return data_list # 获取请求配置信息 def __getConfig(self): with open(self.__config_file, "r",encoding="utf-8") as load_f: load_dict = json.load(load_f) return load_dict # 设置配置项 def __setConfig(self,key,value): self.__config_dict[key] = value print(self.__config_dict) with open(self.__config_file,'w',encoding="utf-8") as f: f.write(json.dumps(self.__config_dict,ensure_ascii=False))
def getKeywords(self): self.__keywords = input("请输入查询的关键字,多个关键字用“+”连接,默认关键字:环保+污染+投诉,使用默认关键字可直接按Enter:") if len(self.__keywords) == 0: self.__keywords = self.__config_dict['key_words'] else: self.__setConfig("search_key",self.__keywords)
# 获取请求的URL def __getUrl(self): base_url = self.__config_dict['base_url'] # 组装查询参数 url = base_url + "&key=" + self.__keywords return url

- REST服务端(目前服务没有暴露很多,但相应服务实现都已经实现)

#!/usr/bin/env python # -*- coding:utf-8 -*-from flask import Flask,jsonify,abort,requestfrom changshuo108.shangyu.Shangyh108 import Shangyh108
app = Flask(__name__)# 支持中文app.config['JSON_AS_ASCII'] = Falseshangyue = Shangyh108()@app.route('/shangyu108/api/desc',methods=['GET'])def get_desc(): return shangyue.getDesc()
@app.route('/shangyu108/api/first_page',methods=['GET'])def get_firstPage(): return jsonify({'data':shangyue.getFirstPageText('')})
@app.route('/shangyu108/api/page',methods=['POST'])def get_article(): if not request.json or not 'url' in request.json: abort(400) print(request.json['url']) return jsonify({'data':shangyue.getNextPage(request.json['url'])})
if __name__ == '__main__': app.run(debug=True)
公众号链接:https://mp.weixin.qq.com/s?__biz=Mzg4MzI3MjM4NQ==&tempkey=MTAxNl9KVjVnVCtVNlo4RUpIZmZXbzBfSVR4dHU4YUhhX3hPNGMxVXdMd1JaQ21OZExlNnNybmJzaVhCT2hkZk85RzZKbzRlYWxFcEk1U2g5bmN4cWJ1QlNmNEdmWlBvVWxGTER2NDM5NjdWa1VIaDVWZlFyUF9EVmtYM0lmNnplRzRjanZsWEo4RUlESTg2YlFkVjBxdDFXbzEwR1UtVVpSd2V5U0R1YUVnfn4%3D&chksm=4f48bebe783f37a8622096cf8cb7d5dfbc5d913e3f1694ea601f51eec5aadddee66271739639#rd