「docker實戰篇」python的docker爬蟲技術-python腳本app抓取（13）

時間  2019-12-12
標籤 docker 實戰 python 爬蟲 技術 腳本 app 抓取 欄目 Docker 简体版
原文   原文鏈接

原創文章，歡迎轉載。轉載請註明：轉載自IT人故事會，謝謝！
原文連接地址：「docker實戰篇」python的docker爬蟲技術-python腳本app抓取（13）python

上次已經分析出來具體的app的請求鏈接了，本次主要說說python的開發，抓取APP裏面的信息。源碼：github.com/limingios/d…android


分析app數據包

查看分析ios


解析出來的headergit


夜神配置github


python代碼，爬取分類mongodb


#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/9 11:06
# @Author : lm
# @Url : idig8.com
# @Site : 
# @File : spider_douguomeishi.py
# @Software: PyCharm

import requests

#header內容比較多，由於各個廠家的思路不一樣，
#fiddler爬取出來的字段比較多，有些內容應該是非必填的，只能在實際的時候嘗試註釋一些來試。
def handle_request(url,data):


    header ={
        "client": "4",
        "version": "6916.2",
        "device": "SM-G955N",
        "sdk": "22,5.1.1",
        "imei": "354730010002552",
        "channel": "zhuzhan",
        "mac": "00:FF:E2:A2:7B:58",
        "resolution": "1440*900",
        "dpi":"2.0",
        "android-id":"bcdaf527105cc26f",
        "pseudo-id":"354730010002552",
        "brand":"samsung",
        "scale":"2.0",
        "timezone":"28800",
        "language":"zh",
        "cns":"3",
        "carrier": "Android",
        #"imsi": "310260000000000",
        "user-agent": "Mozilla/5.0 (Linux; Android 5.1.1; SM-G955N Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/39.0.0.0 Mobile Safari/537.36",
        "lon": "105.566938",
        "lat": "29.99831",
        "cid": "512000",
        "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
        "Accept-Encoding": "gzip, deflate",
        "Connection": "Keep-Alive",
        # "Cookie": "duid=58349118",
        "Host": "api.douguo.net",
        #"Content-Length": "65"
    }
    response = requests.post(url=url,headers=header,data=data)
    return response

def handle_index():
    url = "http://api.douguo.net/recipe/flatcatalogs"
    # client=4&_session=1547000257341354730010002552&v=1503650468&_vs=0
    data ={
        "client":"4",
        "_session":"1547000257341354730010002552",
        "v":"1503650468",
        "_vs":"0"
    }
    response = handle_request(url,data)
    print(response.text)

handle_index()

複製代碼

爬取詳情，信息經過分類找到裏面的詳情docker



#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/9 11:06
# @Author : lm
# @Url : idig8.com
# @Site : 
# @File : spider_douguomeishi.py
# @Software: PyCharm
import json

import requests

from multiprocessing import Queue

#建立隊列
queue_list = Queue()


def handle_request(url,data):
    header ={
        "client": "4",
        "version": "6916.2",
        "device": "SM-G955N",
        "sdk": "22,5.1.1",
        "imei": "354730010002552",
        "channel": "zhuzhan",
        "mac": "00:FF:E2:A2:7B:58",
        "resolution": "1440*900",
        "dpi":"2.0",
        "android-id":"bcdaf527105cc26f",
        "pseudo-id":"354730010002552",
        "brand":"samsung",
        "scale":"2.0",
        "timezone":"28800",
        "language":"zh",
        "cns":"3",
        "carrier": "Android",
        #"imsi": "310260000000000",
        "user-agent": "Mozilla/5.0 (Linux; Android 5.1.1; SM-G955N Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/39.0.0.0 Mobile Safari/537.36",
        "lon": "105.566938",
        "lat": "29.99831",
        "cid": "512000",
        "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
        "Accept-Encoding": "gzip, deflate",
        "Connection": "Keep-Alive",
        # "Cookie": "duid=58349118",
        "Host": "api.douguo.net",
        #"Content-Length": "65"
    }
    response = requests.post(url=url,headers=header,data=data)
    return response

def handle_index():
    url = "http://api.douguo.net/recipe/flatcatalogs"
    # client=4&_session=1547000257341354730010002552&v=1503650468&_vs=0
    data ={
        "client":"4",
        "_session":"1547000257341354730010002552",
        "v":"1503650468",
        "_vs":"0"
    }
    response = handle_request(url,data)
    # print(response.text)
    index_response_dic = json.loads(response.text)
    for item_index in index_response_dic["result"]["cs"]:
        # print(item_index)
        for item_index_cs in item_index["cs"]:
            # print(item_index_cs)
            for item in item_index_cs["cs"]:
                #print(item)
                data_2 ={
                    "client":"4",
                    "_session":"1547000257341354730010002552",
                    "keyword":item["name"],
                    "_vs ":"400"
                }
                #print(data_2)
                queue_list.put(data_2)


handle_index()
print(queue_list.qsize())
複製代碼
image.png
image.png

分類菜譜內部的詳情信息json

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/9 11:06
# @Author : lm
# @Url : idig8.com
# @Site : 
# @File : spider_douguomeishi.py
# @Software: PyCharm
import json

import requests

from multiprocessing import Queue

#建立隊列
queue_list = Queue()


def handle_request(url,data):
    header ={
        "client": "4",
        "version": "6916.2",
        "device": "SM-G955N",
        "sdk": "22,5.1.1",
        "imei": "354730010002552",
        "channel": "zhuzhan",
        "mac": "00:FF:E2:A2:7B:58",
        "resolution": "1440*900",
        "dpi":"2.0",
        "android-id":"bcdaf527105cc26f",
        "pseudo-id":"354730010002552",
        "brand":"samsung",
        "scale":"2.0",
        "timezone":"28800",
        "language":"zh",
        "cns":"3",
        "carrier": "Android",
        #"imsi": "310260000000000",
        "user-agent": "Mozilla/5.0 (Linux; Android 5.1.1; SM-G955N Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/39.0.0.0 Mobile Safari/537.36",
        "lon": "105.566938",
        "lat": "29.99831",
        "cid": "512000",
        "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
        "Accept-Encoding": "gzip, deflate",
        "Connection": "Keep-Alive",
        # "Cookie": "duid=58349118",
        "Host": "api.douguo.net",
        #"Content-Length": "65"
    }
    response = requests.post(url=url,headers=header,data=data)
    return response

def handle_index():
    url = "http://api.douguo.net/recipe/flatcatalogs"
    # client=4&_session=1547000257341354730010002552&v=1503650468&_vs=0
    data ={
        "client":"4",
        "_session":"1547000257341354730010002552",
        "v":"1503650468",
        "_vs":"0"
    }
    response = handle_request(url,data)
    # print(response.text)
    index_response_dic = json.loads(response.text)
    for item_index in index_response_dic["result"]["cs"]:
        # print(item_index)
        for item_index_cs in item_index["cs"]:
            # print(item_index_cs)
            for item in item_index_cs["cs"]:
                #print(item)
                data_2 ={
                    "client":"4",
                    #"_session":"1547000257341354730010002552",
                    "keyword":item["name"],
                    "_vs ":"400",
                    "order":"0"
                }
                #print(data_2)
                queue_list.put(data_2)

def handle_caipu_list(data):
    print("當前的食材：",data["keyword"])
    caipu_list_url = "http://api.douguo.net/recipe/s/0/20";
    caipu_response = handle_request(caipu_list_url, data)
    caipu_response_dict = json.loads(caipu_response.text)
    for caipu_item in caipu_response_dict["result"]["list"]:
        caipu_info ={}
        caipu_info["shicai"] = data["keyword"]
        if caipu_item["type"]==13:
            caipu_info["user_name"] = caipu_item["r"]["an"]
            caipu_info["shicai_id"] = caipu_item["r"]["id"]
            caipu_info["describe"] = caipu_item["r"]["cookstory"].replace("\n","").replace(" ","")
            caipu_info["caipu_name"] = caipu_item["r"]["n"]
            caipu_info["zuoliao_list"] = caipu_item["r"]["major"]
            print(caipu_info)
        else:
            continue


handle_index()
handle_caipu_list(queue_list.get())


複製代碼

菜品內部的詳情信息centos



#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/9 11:06
# @Author : lm
# @Url : idig8.com
# @Site : 
# @File : spider_douguomeishi.py
# @Software: PyCharm
import json

import requests

from multiprocessing import Queue

#建立隊列
queue_list = Queue()


def handle_request(url,data):
    header ={
        "client": "4",
        "version": "6916.2",
        "device": "SM-G955N",
        "sdk": "22,5.1.1",
        "imei": "354730010002552",
        "channel": "zhuzhan",
        "mac": "00:FF:E2:A2:7B:58",
        "resolution": "1440*900",
        "dpi":"2.0",
        "android-id":"bcdaf527105cc26f",
        "pseudo-id":"354730010002552",
        "brand":"samsung",
        "scale":"2.0",
        "timezone":"28800",
        "language":"zh",
        "cns":"3",
        "carrier": "Android",
        #"imsi": "310260000000000",
        "user-agent": "Mozilla/5.0 (Linux; Android 5.1.1; SM-G955N Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/39.0.0.0 Mobile Safari/537.36",
        "lon": "105.566938",
        "lat": "29.99831",
        "cid": "512000",
        "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
        "Accept-Encoding": "gzip, deflate",
        "Connection": "Keep-Alive",
        # "Cookie": "duid=58349118",
        "Host": "api.douguo.net",
        #"Content-Length": "65"
    }
    response = requests.post(url=url,headers=header,data=data)
    return response

def handle_index():
    url = "http://api.douguo.net/recipe/flatcatalogs"
    # client=4&_session=1547000257341354730010002552&v=1503650468&_vs=0
    data ={
        "client":"4",
        "_session":"1547000257341354730010002552",
        "v":"1503650468",
        "_vs":"0"
    }
    response = handle_request(url,data)
    # print(response.text)
    index_response_dic = json.loads(response.text)
    for item_index in index_response_dic["result"]["cs"]:
        # print(item_index)
        for item_index_cs in item_index["cs"]:
            # print(item_index_cs)
            for item in item_index_cs["cs"]:
                #print(item)
                data_2 ={
                    "client":"4",
                    #"_session":"1547000257341354730010002552",
                    "keyword":item["name"],
                    "_vs ":"400",
                    "order":"0"
                }
                #print(data_2)
                queue_list.put(data_2)

def handle_caipu_list(data):
    print("當前的食材：",data["keyword"])
    caipu_list_url = "http://api.douguo.net/recipe/s/0/20";
    caipu_response = handle_request(caipu_list_url, data)
    caipu_response_dict = json.loads(caipu_response.text)
    for caipu_item in caipu_response_dict["result"]["list"]:
        caipu_info ={}
        caipu_info["shicai"] = data["keyword"]
        if caipu_item["type"]==13:
            caipu_info["user_name"] = caipu_item["r"]["an"]
            caipu_info["shicai_id"] = caipu_item["r"]["id"]
            caipu_info["describe"] = caipu_item["r"]["cookstory"].replace("\n","").replace(" ","")
            caipu_info["caipu_name"] = caipu_item["r"]["n"]
            caipu_info["zuoliao_list"] = caipu_item["r"]["major"]
            #print(caipu_info)
            detail_url = "http://api.douguo.net/recipe/detail/"+ str(caipu_info["shicai_id"])
            detail_data ={
                "client":"4",
                "_session":"1547000257341354730010002552",
                "author_id":"0",
                "_vs":"2803",
                "ext":'{"query": {"kw": "'+data["keyword"]+'", "src": "2803", "idx": "1", "type": "13", "id": '+str(caipu_info["shicai_id"])+'}}'
            }

            detail_reponse = handle_request(detail_url,detail_data)
            detail_reponse_dic = json.loads(detail_reponse.text)
            caipu_info["tips"] = detail_reponse_dic["result"]["recipe"]["tips"]
            caipu_info["cookstep"] = detail_reponse_dic["result"]["recipe"]["cookstep"]
            print(json.dumps(caipu_info))

        else:
            continue


handle_index()
handle_caipu_list(queue_list.get())


複製代碼

將數據保存在mongodb中

  • 經過vagrant 安裝虛擬機
vagrant up
複製代碼
  • 進入虛擬機

ip 192.168.66.100api


su -
#密碼：vagrant
docker
複製代碼

  • 拉取mongodb的鏡像

hub.docker.com/r/bitnami/m…
默認端口：27017

docker pull bitnami/mongodb:latest
複製代碼

  • 建立mongodb的容器
mkdir bitnami
cd bitnami
mkdir mongodb
docker run -d -v /path/to/mongodb-persistence:/root/bitnami -p 27017:27017 bitnami/mongodb:latest

#關閉防火牆
systemctl stop firewalld
複製代碼

用第三方工具鏈接


鏈接mongodb的工具

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/11 0:53
# @Author : liming
# @Site : 
# @File : handle_mongodb.py
# @url : idig8.com
# @Software: PyCharm

import pymongo
from pymongo.collection import Collection

class Connect_mongo(object):
    def __init__(self):
        self.client = pymongo.MongoClient(host="192.168.66.100",port=27017)
        self.db_data = self.client["dou_guo_mei_shi"]

    def insert_item(self,item):
        db_collection = Collection(self.db_data,'dou_guo_mei_shi_item')
        db_collection.insert(item)

# 暴露出來
mongo_info = Connect_mongo()
複製代碼

python爬取的數據經過mongo的工具保存到centos7的docker鏡像中



#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/9 11:06
# @Author : lm
# @Url : idig8.com
# @Site : 
# @File : spider_douguomeishi.py
# @Software: PyCharm
import json

import requests

from multiprocessing import Queue
from handle_mongo import mongo_info

#建立隊列
queue_list = Queue()


def handle_request(url,data):
    header ={
        "client": "4",
        "version": "6916.2",
        "device": "SM-G955N",
        "sdk": "22,5.1.1",
        "imei": "354730010002552",
        "channel": "zhuzhan",
        "mac": "00:FF:E2:A2:7B:58",
        "resolution": "1440*900",
        "dpi":"2.0",
        "android-id":"bcdaf527105cc26f",
        "pseudo-id":"354730010002552",
        "brand":"samsung",
        "scale":"2.0",
        "timezone":"28800",
        "language":"zh",
        "cns":"3",
        "carrier": "Android",
        #"imsi": "310260000000000",
        "user-agent": "Mozilla/5.0 (Linux; Android 5.1.1; SM-G955N Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/39.0.0.0 Mobile Safari/537.36",
        "lon": "105.566938",
        "lat": "29.99831",
        "cid": "512000",
        "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
        "Accept-Encoding": "gzip, deflate",
        "Connection": "Keep-Alive",
        # "Cookie": "duid=58349118",
        "Host": "api.douguo.net",
        #"Content-Length": "65"
    }
    response = requests.post(url=url,headers=header,data=data)
    return response

def handle_index():
    url = "http://api.douguo.net/recipe/flatcatalogs"
    # client=4&_session=1547000257341354730010002552&v=1503650468&_vs=0
    data ={
        "client":"4",
        "_session":"1547000257341354730010002552",
        "v":"1503650468",
        "_vs":"0"
    }
    response = handle_request(url,data)
    # print(response.text)
    index_response_dic = json.loads(response.text)
    for item_index in index_response_dic["result"]["cs"]:
        # print(item_index)
        for item_index_cs in item_index["cs"]:
            # print(item_index_cs)
            for item in item_index_cs["cs"]:
                #print(item)
                data_2 ={
                    "client":"4",
                    #"_session":"1547000257341354730010002552",
                    "keyword":item["name"],
                    "_vs ":"400",
                    "order":"0"
                }
                #print(data_2)
                queue_list.put(data_2)

def handle_caipu_list(data):
    print("當前的食材：",data["keyword"])
    caipu_list_url = "http://api.douguo.net/recipe/s/0/20";
    caipu_response = handle_request(caipu_list_url, data)
    caipu_response_dict = json.loads(caipu_response.text)
    for caipu_item in caipu_response_dict["result"]["list"]:
        caipu_info ={}
        caipu_info["shicai"] = data["keyword"]
        if caipu_item["type"]==13:
            caipu_info["user_name"] = caipu_item["r"]["an"]
            caipu_info["shicai_id"] = caipu_item["r"]["id"]
            caipu_info["describe"] = caipu_item["r"]["cookstory"].replace("\n","").replace(" ","")
            caipu_info["caipu_name"] = caipu_item["r"]["n"]
            caipu_info["zuoliao_list"] = caipu_item["r"]["major"]
            #print(caipu_info)
            detail_url = "http://api.douguo.net/recipe/detail/"+ str(caipu_info["shicai_id"])
            detail_data ={
                "client":"4",
                "_session":"1547000257341354730010002552",
                "author_id":"0",
                "_vs":"2803",
                "ext":'{"query": {"kw": "'+data["keyword"]+'", "src": "2803", "idx": "1", "type": "13", "id": '+str(caipu_info["shicai_id"])+'}}'
            }

            detail_reponse = handle_request(detail_url,detail_data)
            detail_reponse_dic = json.loads(detail_reponse.text)
            caipu_info["tips"] = detail_reponse_dic["result"]["recipe"]["tips"]
            caipu_info["cookstep"] = detail_reponse_dic["result"]["recipe"]["cookstep"]
            #print(json.dumps(caipu_info))
            mongo_info.insert_item(caipu_info)

        else:
            continue


handle_index()
handle_caipu_list(queue_list.get())


複製代碼

經過python多線程-線程池抓取

  • python3經過concurrent.futures import ThreadPoolExecutor

引用線程池


#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/9 11:06
# @Author : lm
# @Url : idig8.com
# @Site : 
# @File : spider_douguomeishi.py
# @Software: PyCharm
import json

import requests

from multiprocessing import Queue
from handle_mongo import mongo_info
from concurrent.futures import ThreadPoolExecutor


#建立隊列
queue_list = Queue()


def handle_request(url,data):
    header ={
        "client": "4",
        "version": "6916.2",
        "device": "SM-G955N",
        "sdk": "22,5.1.1",
        "imei": "354730010002552",
        "channel": "zhuzhan",
        "mac": "00:FF:E2:A2:7B:58",
        "resolution": "1440*900",
        "dpi":"2.0",
        "android-id":"bcdaf527105cc26f",
        "pseudo-id":"354730010002552",
        "brand":"samsung",
        "scale":"2.0",
        "timezone":"28800",
        "language":"zh",
        "cns":"3",
        "carrier": "Android",
        #"imsi": "310260000000000",
        "user-agent": "Mozilla/5.0 (Linux; Android 5.1.1; SM-G955N Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/39.0.0.0 Mobile Safari/537.36",
        "lon": "105.566938",
        "lat": "29.99831",
        "cid": "512000",
        "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
        "Accept-Encoding": "gzip, deflate",
        "Connection": "Keep-Alive",
        # "Cookie": "duid=58349118",
        "Host": "api.douguo.net",
        #"Content-Length": "65"
    }
    response = requests.post(url=url,headers=header,data=data)
    return response

def handle_index():
    url = "http://api.douguo.net/recipe/flatcatalogs"
    # client=4&_session=1547000257341354730010002552&v=1503650468&_vs=0
    data ={
        "client":"4",
        "_session":"1547000257341354730010002552",
        "v":"1503650468",
        "_vs":"0"
    }
    response = handle_request(url,data)
    # print(response.text)
    index_response_dic = json.loads(response.text)
    for item_index in index_response_dic["result"]["cs"]:
        # print(item_index)
        for item_index_cs in item_index["cs"]:
            # print(item_index_cs)
            for item in item_index_cs["cs"]:
                #print(item)
                data_2 ={
                    "client":"4",
                    #"_session":"1547000257341354730010002552",
                    "keyword":item["name"],
                    "_vs ":"400",
                    "order":"0"
                }
                #print(data_2)
                queue_list.put(data_2)

def handle_caipu_list(data):
    print("當前的食材：",data["keyword"])
    caipu_list_url = "http://api.douguo.net/recipe/s/0/20";
    caipu_response = handle_request(caipu_list_url, data)
    caipu_response_dict = json.loads(caipu_response.text)
    for caipu_item in caipu_response_dict["result"]["list"]:
        caipu_info ={}
        caipu_info["shicai"] = data["keyword"]
        if caipu_item["type"]==13:
            caipu_info["user_name"] = caipu_item["r"]["an"]
            caipu_info["shicai_id"] = caipu_item["r"]["id"]
            caipu_info["describe"] = caipu_item["r"]["cookstory"].replace("\n","").replace(" ","")
            caipu_info["caipu_name"] = caipu_item["r"]["n"]
            caipu_info["zuoliao_list"] = caipu_item["r"]["major"]
            #print(caipu_info)
            detail_url = "http://api.douguo.net/recipe/detail/"+ str(caipu_info["shicai_id"])
            detail_data ={
                "client":"4",
                "_session":"1547000257341354730010002552",
                "author_id":"0",
                "_vs":"2803",
                "ext":'{"query": {"kw": "'+data["keyword"]+'", "src": "2803", "idx": "1", "type": "13", "id": '+str(caipu_info["shicai_id"])+'}}'
            }

            detail_reponse = handle_request(detail_url,detail_data)
            detail_reponse_dic = json.loads(detail_reponse.text)
            caipu_info["tips"] = detail_reponse_dic["result"]["recipe"]["tips"]
            caipu_info["cookstep"] = detail_reponse_dic["result"]["recipe"]["cookstep"]
            #print(json.dumps(caipu_info))
            mongo_info.insert_item(caipu_info)

        else:
            continue


handle_index()
pool = ThreadPoolExecutor(max_workers=20)
while queue_list.qsize()>0:
    pool.submit(handle_caipu_list,queue_list.get())



複製代碼

經過使用代理ip隱藏爬蟲

當app運維人員，發現咱們的一直在請求他們的服務器，極可能就把我們的ip給封了，經過代理ip的方式。隱藏自我。

  • 註冊申請 abuyun.com

一個小時1元，我申請了一個小時我們一塊兒使用下


#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/11 2:40
# @Author : Aries
# @Site : 
# @File : handle_proxy.py
# @Software: PyCharm


#60.17.177.187 代理出來的ip
import  requests
url = 'http://ip.hahado.cn/ip'
proxy = {'http':'http://H79623F667Q3936C:84F1527F3EE09817@http-cla.abuyun.com:9030'}
response = requests.get(url=url,proxies=proxy)
print(response.text)
複製代碼


#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/1/9 11:06
# @Author : lm
# @Url : idig8.com
# @Site : 
# @File : spider_douguomeishi.py
# @Software: PyCharm
import json

import requests

from multiprocessing import Queue
from handle_mongo import mongo_info
from concurrent.futures import ThreadPoolExecutor


#建立隊列
queue_list = Queue()


def handle_request(url,data):
    header ={
        "client": "4",
        "version": "6916.2",
        "device": "SM-G955N",
        "sdk": "22,5.1.1",
        "imei": "354730010002552",
        "channel": "zhuzhan",
        "mac": "00:FF:E2:A2:7B:58",
        "resolution": "1440*900",
        "dpi":"2.0",
        "android-id":"bcdaf527105cc26f",
        "pseudo-id":"354730010002552",
        "brand":"samsung",
        "scale":"2.0",
        "timezone":"28800",
        "language":"zh",
        "cns":"3",
        "carrier": "Android",
        #"imsi": "310260000000000",
        "user-agent": "Mozilla/5.0 (Linux; Android 5.1.1; SM-G955N Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/39.0.0.0 Mobile Safari/537.36",
        "lon": "105.566938",
        "lat": "29.99831",
        "cid": "512000",
        "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
        "Accept-Encoding": "gzip, deflate",
        "Connection": "Keep-Alive",
        # "Cookie": "duid=58349118",
        "Host": "api.douguo.net",
        #"Content-Length": "65"
    }

    proxy = {'http': 'http://H79623F667Q3936C:84F1527F3EE09817@http-cla.abuyun.com:9030'}
    response = requests.post(url=url,headers=header,data=data,proxies=proxy)
    return response

def handle_index():
    url = "http://api.douguo.net/recipe/flatcatalogs"
    # client=4&_session=1547000257341354730010002552&v=1503650468&_vs=0
    data ={
        "client":"4",
        "_session":"1547000257341354730010002552",
        "v":"1503650468",
        "_vs":"0"
    }
    response = handle_request(url,data)
    # print(response.text)
    index_response_dic = json.loads(response.text)
    for item_index in index_response_dic["result"]["cs"]:
        # print(item_index)
        for item_index_cs in item_index["cs"]:
            # print(item_index_cs)
            for item in item_index_cs["cs"]:
                #print(item)
                data_2 ={
                    "client":"4",
                    #"_session":"1547000257341354730010002552",
                    "keyword":item["name"],
                    "_vs ":"400",
                    "order":"0"
                }
                #print(data_2)
                queue_list.put(data_2)

def handle_caipu_list(data):
    print("當前的食材：",data["keyword"])
    caipu_list_url = "http://api.douguo.net/recipe/s/0/20";
    caipu_response = handle_request(caipu_list_url, data)
    caipu_response_dict = json.loads(caipu_response.text)
    for caipu_item in caipu_response_dict["result"]["list"]:
        caipu_info ={}
        caipu_info["shicai"] = data["keyword"]
        if caipu_item["type"]==13:
            caipu_info["user_name"] = caipu_item["r"]["an"]
            caipu_info["shicai_id"] = caipu_item["r"]["id"]
            caipu_info["describe"] = caipu_item["r"]["cookstory"].replace("\n","").replace(" ","")
            caipu_info["caipu_name"] = caipu_item["r"]["n"]
            caipu_info["zuoliao_list"] = caipu_item["r"]["major"]
            #print(caipu_info)
            detail_url = "http://api.douguo.net/recipe/detail/"+ str(caipu_info["shicai_id"])
            detail_data ={
                "client":"4",
                "_session":"1547000257341354730010002552",
                "author_id":"0",
                "_vs":"2803",
                "ext":'{"query": {"kw": "'+data["keyword"]+'", "src": "2803", "idx": "1", "type": "13", "id": '+str(caipu_info["shicai_id"])+'}}'
            }

            detail_reponse = handle_request(detail_url,detail_data)
            detail_reponse_dic = json.loads(detail_reponse.text)
            caipu_info["tips"] = detail_reponse_dic["result"]["recipe"]["tips"]
            caipu_info["cookstep"] = detail_reponse_dic["result"]["recipe"]["cookstep"]
            #print(json.dumps(caipu_info))
            mongo_info.insert_item(caipu_info)

        else:
            continue


handle_index()
pool = ThreadPoolExecutor(max_workers=2)
while queue_list.qsize()>0:
    pool.submit(handle_caipu_list,queue_list.get())

複製代碼

PS：本次是app數據抓取的入門。首先是經過模擬器的代理服務，到本地的電腦（安裝fiddler），這樣fiddler就能夠抓取數據了，分析數據這塊要憑藉本身的經驗找到對應的url，若是能分析到url，基本爬蟲就寫一半。封裝請求頭。經過fiddler獲取的。裏面header內容比較多，嘗試刪除最簡化，也是一種反爬蟲的策略，有的數據放進去到容易被發現是爬蟲了，例如cookies等等，可是有的爬蟲爬取數據須要cookies。經過代理的方式設置代理ip，防止爬取過程當中同一個ip，一直請求一個接口被發現是爬蟲。引入了隊列的目的就是爲了使用線程池的時候方便提取。而後放入mongodb中。這樣使用多線程的app數據就完成了。

相關文章
相關標籤/搜索
每日一句
    每一个你不满意的现在，都有一个你没有努力的曾经。
本站公眾號
   歡迎關注本站公眾號,獲取更多信息
聯繫我們 最近搜索 最新文章 沪ICP备13005482号-10 MyBatis教程 SQL 教程 MySQL教程 Java 教程 Thymeleaf 教程 Hibernate教程 Spring教程 Redis教程