Python Ajax爬虫

时间:2022-05-23 BoBo yeah 人气:0

1. 抓取街拍图片

2. 分析街拍图片结构

keyword: 街拍
pd: atlas
dvpf: pc
aid: 4916
page_num: 1
search_json: {"from_search_id":"20220104115420010212192151532E8188","origin_keyword":"街拍","image_keyword":"街拍"}
rawJSON: 1
search_id: 202201041159040101501341671A4749C4

可以找到规律，page_num从1开始累加，其他参数不变

3. 按功能不同编写不同方法组织代码

3.1 获取网页json格式数据

def get_page(page_num):
    global headers
    headers = {
        'Host': 'so.toutiao.com',
        #'Referer': 'https://so.toutiao.com/search?keyword=%E8%A1%97%E6%8B%8D&pd=atlas&dvpf=pc&aid=4916&page_num=0&search_json={%22from_search_id%22:%22202112272022060101510440283EE83D67%22,%22origin_keyword%22:%22%E8%A1%97%E6%8B%8D%22,%22image_keyword%22:%22%E8%A1%97%E6%8B%8D%22}',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
        'X-Requested-With': 'XMLHttpRequest',
        'Cookie': 'msToken=S0DFBkZ9hmyLOGYd3_QjhhXgrm38qTyOITnkNb0t_oavfbVxuYV1JZ0tT5hLgswSfmZLFD6c2lONm_5TomUQXVXjen7CIxM2AGwbhHRYKjhg; _S_DPR=1.5; _S_IPAD=0; MONITOR_WEB_ID=7046351002275317255; ttwid=1%7C0YdWalNdIiSpIk3CvvHwV25U8drq3QAj08E8QOApXhs%7C1640607595%7C720e971d353416921df127996ed708931b4ae28a0a8691a5466347697e581ce8; _S_WIN_WH=262_623'
    }
    params = {
        'keyword': '街拍',
        'pd': 'atlas',
        'dvpf': 'pc',
        'aid': '4916',
        'page_num': page_num,
        'search_json': '%7B%22from_search_id%22%3A%22202112272022060101510440283EE83D67%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': '2021122721183101015104402851E3883D'
    }
    url = 'https://so.toutiao.com/search?' + urlencode(params)
    print(url)
    try:
        response=requests.get(url,headers=headers,params=params)
        if response.status_code == 200:
        #if response.content:
            #print(response.json())
            return response.json()
    except requests.ConnectionError:
        return None

3.2 从json格式数据提取街拍图片

def get_images(json):
    images = json.get('rawData').get('data')
    for image in images:
        link = image.get('img_url')
        yield link

3.3 将街拍图片以其md5码命名并保存图片

实现一个保存图片的方法save_image()，其中 item 就是前面 get_images() 方法返回的一个字典。在该方法中，首先根据 item 的 title 来创建文件夹，然后请求这个图片链接，获取图片的二进制数据，以二进制的形式写入文件。图片的名称可以使用其内容的 MD5 值，这样可以去除重复。相关

代码如下：

def save_image(link):
    data = requests.get(link).content
    with open(f'./image/{md5(data).hexdigest()}.jpg', 'wb')as f:#使用data的md5码作为图片名
        f.write(data)

3.4 main()调用其他函数

def main(page_num):
    json = get_page(page_num)
    for link in get_images(json):
        #print(link)
        save_image(link)

4 抓取20page今日头条街拍图片数据

这里定义了分页的起始页数和终止页数，分别为GROUP_START 和 GROUP_END，还利用了多线程的线程池，调用其 map() 方法实现程下载。

if __name__ == '__main__':
    GROUP_START = 1
    GROUP_END = 20
    pool = Pool()
    groups = ([x for x in range(GROUP_START, GROUP_END + 1)])
    #print(groups)
    pool.map(main, groups)
    pool.close()
    pool.join()

import requests
from urllib.parse import urlencode
from hashlib import md5
from multiprocessing.pool import Pool
def get_page(page_num):
    global headers
    headers = {
        'Host': 'so.toutiao.com',
        #'Referer': 'https://so.toutiao.com/search?keyword=%E8%A1%97%E6%8B%8D&pd=atlas&dvpf=pc&aid=4916&page_num=0&search_json={%22from_search_id%22:%22202112272022060101510440283EE83D67%22,%22origin_keyword%22:%22%E8%A1%97%E6%8B%8D%22,%22image_keyword%22:%22%E8%A1%97%E6%8B%8D%22}',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
        'X-Requested-With': 'XMLHttpRequest',
        'Cookie': 'msToken=S0DFBkZ9hmyLOGYd3_QjhhXgrm38qTyOITnkNb0t_oavfbVxuYV1JZ0tT5hLgswSfmZLFD6c2lONm_5TomUQXVXjen7CIxM2AGwbhHRYKjhg; _S_DPR=1.5; _S_IPAD=0; MONITOR_WEB_ID=7046351002275317255; ttwid=1%7C0YdWalNdIiSpIk3CvvHwV25U8drq3QAj08E8QOApXhs%7C1640607595%7C720e971d353416921df127996ed708931b4ae28a0a8691a5466347697e581ce8; _S_WIN_WH=262_623'
    }
    params = {
        'keyword': '街拍',
        'pd': 'atlas',
        'dvpf': 'pc',
        'aid': '4916',
        'page_num': page_num,
        'search_json': '%7B%22from_search_id%22%3A%22202112272022060101510440283EE83D67%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': '2021122721183101015104402851E3883D'
    }
    url = 'https://so.toutiao.com/search?' + urlencode(params)
    print(url)
    try:
        response=requests.get(url,headers=headers,params=params)
        if response.status_code == 200:
        #if response.content:
            #print(response.json())
            return response.json()
    except requests.ConnectionError:
        return None

def get_images(json):
    images = json.get('rawData').get('data')
    for image in images:
        link = image.get('img_url')
        yield link


def save_image(link):
    data = requests.get(link).content
    with open(f'./image/{md5(data).hexdigest()}.jpg', 'wb')as f:#使用data的md5码作为图片名
        f.write(data)


def main(page_num):
    json = get_page(page_num)
    for link in get_images(json):
        #print(link)
        save_image(link)


if __name__ == '__main__':
    GROUP_START = 1
    GROUP_END = 20
    pool = Pool()
    groups = ([x for x in range(GROUP_START, GROUP_END + 1)])
    #print(groups)
    pool.map(main, groups)
    pool.close()
    pool.join()

加载全部内容