分享一个简单的爬虫

实现对今日头条街拍近400条数据的爬取，感兴趣的朋友可以尝试一下

import requests

from urllib.parse import urlencode
import os
from hashlib import md5
from multiprocessing.pool import Pool

user_agent='Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
headers = { 'User-Agent' : user_agent }

def get_page(offset):
    params = {
        'offset': offset,
        'format': 'json',
        'keyword': '街拍',
        'autoload': 'true',
        'count': '20',
        'cur_tab': '1',
        
    }
    url = 'http://www.toutiao.com/search_content/?' + urlencode(params)
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError:
        return None

def get_images(json):
    if json.get('data'):
        for item in json.get('data'):
            title = item.get('title')
            images = item.get('image_list')
            if title and images:
                for image in images:
                    yield {
                        'image': image.get('url'),
                        'title': title
                    }


def save_image(item):
    if not os.path.exists(item.get('title')):
        os.mkdir(item.get('title'))
    try:
        url = 'http:' + item.get('image')
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            file_path = '{0}/{1}.{2}'.format(item.get('title'), md5(response.content).hexdigest(), 'jpg') 
            if not os.path.exists(file_path):
                with open(file_path, 'wb') as f:
                    f.write(response.content)
            else:
                print('Already Download', file_path)
    except requests.ConnectionError:
        print('Failed to save Image')

def main(offset):
    json = get_page(offset)
    if json:
        for item in get_images(json):
            # print(item)
            save_image(item)

GROUP_START = 1
GROUP_END = 20

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