1. 首页
  2. 分类
  3. 个人笔记

python爬虫+IP代理

作者：拾光 分类：个人笔记 字数：7943 
"""
Created on Wed Nov 23 00:03:30 2022

@author: fch
"""
import time

'''
网站网址：https://m.7160.top/rentiyishu/
'''
import random
from pyquery import PyQuery as pq
import requests
import os
from joblib import Parallel, delayed
import socket
socket.setdefaulttimeout(10)


# 忽略requests证书警告
from requests.packages.urllib3.exceptions import InsecureRequestWarning
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)

requests.DEFAULT_RETRIES = 5  # 增加重试连接次数

IP_list=[]
with open('./IP代理池.txt','r') as f:
    for line in f:
        line = line.strip('\n')  # 删除换行符
        IP_list.append(line)
f.close()

'''
random随机读取到后为字符串类型，用eval转回字典
'''
# proxie = eval(random.choice(IP_list))

user_agent_list = [
        'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0',
        'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko',
        'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)',
        'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
        'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11',
        'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
        'Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
        'Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
        'Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
        'Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1',
        'MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1',
        'Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10',
        'Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13',
        'Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+',
        'Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0',
        'Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124',
        'Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)',
        'UCWEB7.0.2.37/28/999',
        'NOKIA5700/ UCWEB7.0.2.37/28/999',
        'Openwave/ UCWEB7.0.2.37/28/999',
        'Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999',
        'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25',
    ]

def Res_url(url):
    requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
    headers = {'User-Agent': random.choice(user_agent_list),
               'Referer': 'https://m.7160.top/rentiyishu/',
               "Connection": "close"}

    try:
        s=requests.session()
        s.keep_alive = False
        r = s.get(url, headers=headers, proxies=eval(random.choice(IP_list)), timeout=(5, 10),verify=False,allow_redirects=False)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print(url)
        return 'over'

'''
爬取首页中所有伪图片的链接地址和名称，返回成列表
'''
def Parse_page(html):
    page_url_list,fil_name_list=[],[]
    doc = pq(html)
    items = doc('.listUll2 li').items()
    for item in items:
        page_url_list.append(item('div a').attr('href'))
        fil_name_list.append(item('p').text())
    return page_url_list,fil_name_list


def Get_img(page_url, file_name):
    num = 1
    base_url = page_url.split('.')
    while True:
        if num == 1:
            url = page_url
        else:
            url = base_url[0] + '.' + base_url[1] + '.' + base_url[2] + '_' + str(num) + '.' + base_url[3]
        time.sleep(1)
        html = Res_url(url)
        if html != 'over':
            doc = pq(html)
            img_url = doc('.ArticleBox img').attr('src')
            img_basename = doc('.ArticleBox img').attr('alt')
            if img_basename==None:
                img_name=img_basename
            else:
                img_name=img_basename.replace('/','')
            if img_url == None:
                num += 1
            else:
                Save_img(img_url, file_name, img_name)
                num += 1
        else:
            break   #跳出while循环


def Save_img(img_url, file_name, img_name):
    time.sleep(1)
    requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
    headers = {'User-Agent': random.choice(user_agent_list),
               'Referer': 'https://m.7160.top/rentiyishu/',
               "Connection": "close"}
    houzui = img_url.split('.')[-1]
    addr = './images_3/' + file_name
    if not os.path.isdir(addr):
        os.makedirs(addr)
    r=requests.get(img_url, headers=headers, proxies=eval(random.choice(IP_list)), verify=False).content
    if r.status_code==200:
        with open('./images_3/{}/{}.{}'.format(file_name, img_name, houzui), 'wb') as f:
            f.write(r.content)
            f.close()
    else:
        print('图片地址不存在')


def main():
    page_num = 1
    base_url = 'https://m.7160.top/rentiyishu/index'
    while True:
        if page_num == 1:
            url = base_url + '.html'
        else:
            url = base_url + '_' + str(page_num) + '.html'
        html = Res_url(url)
        if html != 'over':
            print('保存第', page_num, '页')
            page_url_list, file_name_list=Parse_page(html)
            '''
            多线程：n_jobs=30即同时30个线程
            '''
            Parallel(n_jobs=5)(delayed(Get_img)(page_url,file_name) for page_url,file_name in zip(page_url_list,file_name_list))
        else:
            print('程序结束')
            return '程序结束'
        page_num += 1
main()

IP代理池

作者：拾光 分类：个人笔记 字数：2366 
import requests
from bs4 import BeautifulSoup
import time
'''
IP代理网站的页数
'''
num=51


list_ip = []
list_port = []
list_type=[]
list_headers_ip = []


def check_ip(list_ip):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36 Edg/91.0.864.71',
        'Connection': 'close',
        'Referer': 'https://m.7160.top/rentiyishu/'
    }
    # url = 'https://www.baidu.com'  # 以百度为例，检测IP的可行性
    url = 'https://pic.99ym.cn/d/file/202009/mz1kqud4v2i.jpg'

    can_use = []
    for ip in list_ip:
        try:
            response = requests.get(url=url, headers=headers, proxies=ip, timeout=3, verify=False)  # 在0.1秒之内请求百度的服务器
            if response.status_code == 200:
                can_use.append(ip)
        except Exception as e:
            print(e)

    return can_use


for start in range(1, num):

    url = 'https://www.kuaidaili.com/free/inha/{}/'.format(start)  # 每页15个数据，共爬取10页
    print("正在处理url: ", url)

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36 Edg/91.0.864.71'}
    response = requests.get(url=url, headers=headers)

    soup = BeautifulSoup(response.text, 'html.parser')

    ip = soup.select('#list > table > tbody > tr > td:nth-child(1)')
    port = soup.select('#list > table > tbody > tr > td:nth-child(2)')
    type = soup.select('#list > table > tbody > tr > td:nth-child(4)')
    for i in ip:
        list_ip.append(i.get_text())
    for i in port:
        list_port.append(i.get_text())
    for i in type:
        list_type.append(i.get_text())
    time.sleep(0.5)  # 防止爬取太快，数据爬取不全

# 代理ip的形式:        'http':'http://119.14.253.128:8088'

for i in range(len(list_ip)):
    if list_type[i]=='HTTP':
        proxies = {
            'HTTP':'http://'+list_ip[i]+':'+list_port[i]
        }
    else:
        proxies = {
            'HTTPS': 'https://' + list_ip[i] + ':' + list_port[i]
        }
    list_headers_ip.append(proxies)
can_use = check_ip(list_headers_ip)
print('能用的代理IP为：', can_use)
print('能用的代理IP数量为：', len(can_use))

with open('./IP代理池.txt','w') as f:
    for i in can_use:
        f.write(str(i)+'\n')
f.close()

图片爬虫（代理ip）

作者：拾光 分类：个人笔记 字数：3334 
# -*- coding: utf-8 -*-
"""
Created on Sat Nov 19 22:44:37 2022

@author: fch
"""

import random
from pyquery import PyQuery as pq
import requests
import os
import time
import json


proxies=[
         {'HTTP':'http://122.140.5.115:9999'},
         {'HTTP':'http://113.101.96.66:8080'},
         {'HTTP':'http://113.124.86.24:9999'},
         {'HTTP':'http://121.13.252.58:41564'},
         {'HTTP':'http://61.216.185.88:60808'},
         {'HTTP':'http://58.20.184.187:9091'},
         {'HTTP':'http://183.236.123.242:8060'},
         {'HTTP':'http://116.9.163.205:58080'},
         {'HTTP':'http://222.74.73.202:42055'},
         {'HTTP':'http://183.247.202.208:30001'},
         {'HTTP':'http://39.108.101.55:1080'},
         {'HTTP':'http://47.105.91.226:8118'},
         ]
proxie=random.choice(proxies)
user_agent_list = ['Chrome/86.0.4240.198',
                   'Chrome/101.0.4951.64',
                   'Chrome/96.0.4664.45',
                   'Chrome/94.0.4606.41'
                   ]
headers = {'User-Agent': random.choice(user_agent_list)}
list1 = [
        "Chrome/68.0.3440.106",
        "Chrome/67.0.3396.99",
        "Chrome/64.0.3282.186",
        "Chrome/62.0.3202.62",
        "Chrome/45.0.2454.101"
    ]


header={'User-Agent': random.choice(list1),
        'Referer':'http://81.68.202.74/',
        'sec-ch-ua': 'Google Chrome',
        'sec-ch-ua-platform':'Windows'
        }
base_url = 'http://81.68.202.74/datu/page/'

# verify=False忽略SSL警告
def Base_page(Page_num):
    url = base_url + str(Page_num)
    try:
        r = requests.get(url, headers=headers,proxies=proxie)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('ERROR!!!')


def Page_url(fir_html):
    doc = pq(fir_html)
    items = doc('.posts-wrapper .entry-media').items()
    num = 1
    for item in items:
        page_url=item('a').attr('href')
        fil_name=item('.lazyload').attr('alt').replace(":","")
        # print(fil_name,page_url)
        print('------ 个数：',num,'------')
        Parse_img(page_url, fil_name)
        num+=1


def Parse_img(page_url,fil_name):
    time.sleep(0.25)
    i=1
    r = requests.get(page_url, headers=headers,proxies=proxie)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    sec_html=r.text
    doc=pq(sec_html)
    items=doc('.entry-content p img').items()
    for item in items:
        dict={
            'url':item.attr('src'),
            'name':item.attr('title')
        }
        print("保存第",i,'张图')
        i+=1
        time.sleep(1.25)
        Save_img(dict,fil_name)

def Save_img(dic,fil_name):
    url=dic['url']
    # time.sleep(0.25)
    data = requests.get(url,headers=header,proxies=proxie).content
    name=dic['name']
    houzui=url.split('.')[-1]
    addr='./images_2/'+fil_name
    if not os.path.isdir(addr):
        os.makedirs(addr)
    with open('./images_2/{}/{}.{}'.format(fil_name,name,houzui),'wb') as f:
        f.write(data)

def main():
    #左闭右开，到21页
    for Page_num in range(1,22):
        print("*************第",Page_num,'页*************')
        fir_html = Base_page(Page_num)
        Page_url(fir_html)
    print("结束！")

main()

Ajax数据爬取

作者：拾光 分类：个人笔记 字数：1703 
from urllib.parse import urlencode
import requests
import re

def Get_page(page_num):
    headers={
        'Host':'so.toutiao.com',
        'user-agent':'Mozilla/5.0',
        'cookie':'tt=acd600b5ac865033f0ee83a63ed44675; '
    }
    base_url='https://so.toutiao.com/search?'
    params = {
        'keyword': '街拍',
        'pd': 'atlas',
        'dvpf': 'pc',
        'aid': '4916',
        'page_num': page_num,
        'search_json': '%7B%22from_search_id%22%3A%2220220104115420010212192151532E8188%22%2C%22origin_keyword%22%3A%22%E8%A1%97%E6%8B%8D%22%2C%22image_keyword%22%3A%22%E8%A1%97%E6%8B%8D%22%7D',
        'rawJSON': 1,
        'search_id': '2022062517173701021219402539E36546'
    }
    url=base_url+urlencode(params)
    try:
        r=requests.get(url,headers=headers)
        if r.status_code==200:
            return r.json()
    except:
        print('Failed!')

def get_images(json):
    images = json['rawData']['data']
    for image in images:
        yield {
            'name': image['text'],
            'url':image['img_url']
        }

def save_image(dict):
    data=requests.get(dict['url']).content
#把“和 ：都替换成‘，’，否则python路径会识别错误
    name=dict['name'].replace(':',',')
    name=name.replace('"',',')
    name=name.replace('?','')
    name=name.split('|')[-1]  #碰到‘|’就取最后一个
    houzui=dict['url'].split('.')[-1]   #截取后缀，比如JPEG，png等图片的格式名称
    with open("./images/{}.{}".format(name,houzui),'wb') as f:
        f.write(data)

def main():
    for page_num in range(1,20):
        json=Get_page(page_num)
        dict=get_images(json)
        for d in dict:
            save_image(d)


main()

selenium爬虫实例

作者：拾光 分类：个人笔记 字数：2695 
import pymysql
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from pyquery import PyQuery as pq
import pymongo

'''链接mongodb'''
client=pymongo.MongoClient("mongodb://*********:27017")
db=client.test
col=db.taobao

'''连接mysql'''
db=pymysql.Connect(host='*********',user='root',password='*********',port=3306,db='xiaomishop')
cursor=db.cursor()
table='taobao'

'''初始url'''
kw='iPad'    #关键词
url='https://s.taobao.com/search?q='+kw

driver=webdriver.Chrome()  #指定浏览器对象
wait=WebDriverWait(driver,50)  #最大等待时长

def Get_page(page_num):
    '''
    获取page_num页的页面信息(html)
    :param page_num:
    :return: Null
    '''
    print('='*25,'正在爬取第',page_num,'页','='*25)
    try:
        driver.get(url)
        input = wait.until(EC.presence_of_element_located((By.CLASS_NAME,'J_Input')))  # 直到定位到搜索框
        submit=wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'J_Submit')))    #直到定位到能点击‘确定’
        input.clear()
        input.send_keys(page_num)
        submit.click()
        Get_product()
    except TimeoutError:
        Get_page(page_num)

def Get_product():
    '''
    获取每页上所有商品的名称、价格、图片、购买量、店铺名称、店铺位置
    :return:Null
    '''
    html=driver.page_source
    doc=pq(html)
    items=doc('.J_MouserOnverReq').items()
    for item in items:
        product={
            'name': item.find('.ctx-box .row-2 a').text(),
            'pic_img':item.find('.pic-box-inner .J_Itemlist_Pic_657878599145').attr('src'),
            'price':item.find('.ctx-box .row-1 strong').text(),
            'nums':item.find('.ctx-box .row-1 .deal-cnt').text(),
            'shop':item.find('.ctx-box .row-3 .shop span').text(),
            'location':item.find('.ctx-box .row-3 .location').text()
        }
        # write_to_mongodb(product)
        # write_to_mysql(product)
        print(product)

def write_to_mongodb(dic):
    '''
    字典结果保存到MongoDB
    :param dic:
    :return: Null
    '''
    col.insert_one(dic)

def write_to_mysql(dic):
    '''
    字典结果写入mysql
    :param dic:
    :return:
    '''
    keys=','.join(dic.keys())
    values=','.join(['%s']*len(dic))
    sql='insert into {table}({keys}) values ({values})'.format(table=table,keys=keys,values=values)
    try:
        if cursor.execute(sql,tuple(dic.values())):
            print('successful')
            db.commit()
    except:
        print('failed')
        db.rollback()


if __name__ == '__main__':
    for page_num in range(1,101):
        Get_page(page_num)
Copyright © 2024 拾光
Powered by Typecho | Theme by Waxy