ajax数据获取

使用requests直接访问页面url返回的信息与页面信息不匹配

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36 Edg/83.0.478.50',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9'
}


response = requests.get('https://dynamic1.scrape.cuiqingcai.com/', headers=headers, verify=False)  # 该网站证书是自行签名的，忽略校验

print(response.text)  # 没有获取到页面信息，因为网站数据是ajax获取的

分析请求获取ajax

import requests
import logging
import json
from os import makedirs
from os.path import exists
# import urllib3

# urllib3.disable_warnings()  # 禁用警告

# import ssl
# ssl._create_default_https_context = ssl._create_unverified_context  # 全局忽略

logging.basicConfig(level=logging.INFO,
                    format='%(asctime)s - %(levelname)s: %(message)s')

INDEX_URL = 'https://dynamic1.scrape.cuiqingcai.com/api/movie/?limit={limit}&offset={offset}'
DETAIL_URL = 'https://dynamic1.scrape.cuiqingcai.com/api/movie/{id}/'
LIMIT = 10
TOTAL_PAGE = 10
RESULTS_DIR = 'results'
exists(RESULTS_DIR) or makedirs(RESULTS_DIR)


headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36 Edg/83.0.478.50',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9'
}


def scrape_api(url):
    logging.info('scraping %s...', url)
    try:
        response = requests.get(url, headers=headers, verify=False)  # 该网站证书是自行签名的，忽略校验
        if response.status_code == 200:
            return response.json()
        logging.error('get invalid status code %s while scraping %s', response.status_code, url)
    except requests.RequestException:
        logging.error('error occurred while scraping %s', url, exc_info=True)  # 传递移除信息


def scrape_index(page):
    url = INDEX_URL.format(limit=LIMIT, offset=LIMIT*(page-1))
    return scrape_api(url)


def scrape_detail(id):
    url = DETAIL_URL.format(id=id)
    return scrape_api(url)


def save_data(data):
    name = data.get('name')
    data_path = f'{RESULTS_DIR}/{name}.json'
    json.dump(data, open(data_path, 'w', encoding='utf-8'), ensure_ascii=False, indent=2)


def main():
    for page in range(1, TOTAL_PAGE + 1):
        index_data = scrape_index(page)
        for item in index_data.get('results'):
            id = item.get('id')
            detail_data = scrape_detail(id)
            # logging.info('detail data %s', detail_data)
            save_data(detail_data)


if __name__ == '__main__':
    main()