Ajax分析 爬虫 Python实现

import requests
import logging
import json
import os
# 目标网站：https://spa1.scrape.center/

# 定义一些基本配置
logging.basicConfig(level=logging.INFO,
                    format='%(asctime)s - %(levelname)s: %(message)s')

# https://spa1.scrape.center/api/movie/?limit=10&offset=0
# https://spa1.scrape.center/api/movie/?limit=10&offset=10
# https://spa1.scrape.center/api/movie/?limit=10&offset=20
# limit一直为10， 正好对应每页10条数据；offset依次变大，页面每加1，offset就加10

INDEX_URL = "https://spa1.scrape.center/api/movie/?limit=10&offset={offset}"
DETAIL_URL = "https://spa1.scrape.center/api/movie/{id}"
TOTAL_PAGE = 2  # 想要爬取的页面数量
RESULE_DIR = "Ajax_result"

if not os.path.exists(RESULE_DIR):
    os.makedirs(RESULE_DIR)


# 定义爬取方法，返回json数据
def scrape_api(url):
    logging.info(f"scraping {url}...")
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.json()
        # 如果上述语句没有执行
        logging.error(f"get invalid status code {response.status_code} while scrape {url}")
    except requests.RequestException:
        logging.error(f"error occurred while scrape {url}", exc_info=True)


# 定义爬取列表页的方法，返回列表页的json数据
def scrape_index(page):
    url = INDEX_URL.format(offset=10 * (page - 1))
    return scrape_api(url)


# 定义爬取详情页的方法，返回详情页的json数据
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"{RESULE_DIR}/{name}.json"
    json.dump(data, open(data_path, mode='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)
            save_data(detail_data)
            logging.info(f"detail data saved successfully")


if __name__ == '__main__':
    main()