python爬虫从小白到高手 Day2 动态页面的爬取

import requests
import re
import json
from hashlib import md5
import os
from bs4 import BeautifulSoup
import pymongo
from config import *
import time



client = pymongo.MongoClient(MONGO_URL, connect=False)
db = client[MONGO_DB]

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

def save_to_mongo(result):
    if db[MONGO_TABLE].insert(result):
        print('save success', result)
        return True
    return False

def download_real_image(url):
    print('downloading---', url)
    try:
        response = requests.get(url)
        if response.status_code == 200:
            save_image(response.content)
        return None
    except RequestException:
        print('request image fail---', url)
        return None


def save_image(content):
    files_path = '{0}/{1}'.format(os.getcwd(), 'tupian')
    if not os.path.exists(files_path):
        os.mkdir(files_path)

    file_path = '{0}/{1}.{2}'.format(files_path, md5(content).hexdigest(), 'jpg')
    if not os.path.exists(file_path):
        with open(file_path, 'wb') as f:
            f.write(content)


def get_real_image_path(article_url):
    headers = {'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'}
    response = requests.get(article_url, headers=headers)
    soup = BeautifulSoup(response.text, "lxml")
    title = soup.select('title')[0].get_text()
    image_pattern = re.compile('gallery: JSON.parse\("(.*?)"\),', re.S)
    result = re.search(image_pattern, response.text)


    if result:
        result = result.group(1).replace('\\', '')
        data = json.loads(result)

        if data and 'sub_images' in data.keys():
            sub_images = data.get('sub_images')
            images_urls = [item.get('url') for item in sub_images]
            for image_url in images_urls: download_real_image(image_url)

            return {
                'title': title,
                'url' : article_url,
                'image_urls': images_urls
            }



def download_image(jsonData):
    if jsonData.get('data'):
        for item in jsonData.get('data'):
            if item and 'article_url' in item.keys():
                title = item.get('title')
                article_url = item.get('article_url')
                result = get_real_image_path(article_url)

                if result: save_to_mongo(result)
            '''
            另外一种数据格式cell，cell type太多，主要分析上面一种
            else:
                #original_page_url
                data = item.get('display')
                #print(display)
                #data = json.loads(display)
                #print(data)
                if data and 'results' in data.keys():
                    results = data.get('results')
                    original_page_urls = [item.get('original_page_url') for item in results]
                # .get('results').get('original_page_url')
                #title = item.get('display').get('title')
                #print(title)
                #print(original_page_urls)'''


def main():

    STARTPAGE = 1
    ENDPAGE = 2

    for i in range(STARTPAGE, ENDPAGE):
        time.sleep(1)
        offset = i * 20
        jsonData = get_page(offset)
        download_image(jsonData)

if __name__ == "__main__":
    main()

MONGO_URL = 'localhost'

MONGO_DB = 'jiepai'

MONGO_TABLE = 'jiepai'

GROUP_START = 0

GROUP_END = 20

KEYWORD = '街拍'