论坛 › Python交流 › 比葫芦画瓢写的电影信息爬取的代码并保存到数据库

python小小白哟 发表于 2023-7-6 17:59:06

比葫芦画瓢写的电影信息爬取的代码并保存到数据库

需要安装以下库:
pymongorequestsrepyquery urllib logging

import pymongo
import requests
import re
from pyquery import PyQuery as pq
from urllib.parse import urljoin
import logging

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

BASE_URL = 'https://ssr1.scrape.center'
TOTAL_PAGE = 10

def scrape_page(url):
    logging.info('scraping %s...', url)
    try:
      response = requests.get(url)
      if response.status_code == 200:
            return response.text
      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)

def scrape_index(page):
    index_url = f'{BASE_URL}/page/{page}'
    return scrape_page(index_url)

def parse_index(html):
    doc = pq(html)
    links = doc('.el-card .name')
    for link in links.items():
      href = link.attr('href')
      detail_url = urljoin(BASE_URL, href)
      logging.info('get detail url %s', detail_url)
      yield detail_url



def scrape_detail(url):
    return scrape_page(url)

def parse_detail(html):
    doc = pq(html)
    cover = doc('img.cover').attr('src')
    name = doc('a > h2').text()
    categories =
    published_at = doc('.info:contains(上映)').text()
    published_at = re.search('(\d{4}-\d{2}-\d{2})', published_at).group(1) \
      if published_at and re.search('\d{4}-\d{2}-\d{2}', published_at) else None
    drama = doc('.drama p').text()
    score = doc('p.score').text()
    score = float(score) if score else None
    return {
      'cover': cover,
      'name': name,
      'categories': categories,
      'published_at': published_at,
      'drama': drama,
      'score': score
}



client = pymongo.MongoClient(host='localhost', port=27017)
db = client.movies
collection = db.movies_mes

def save_data(data):
    collection.update_one({
    'name': data.get('name')
    }, {
    '$set': data
    }, upsert=True)

def main():
    for page in range(1, TOTAL_PAGE + 1):
      index_html = scrape_index(page)
      detail_urls = parse_index(index_html)
      for detail_url in detail_urls:
            detail_html = scrape_detail(detail_url)
            data = parse_detail(detail_html)
            logging.info('get detail data %s', data)
            logging.info('saving data to mongodb')
            save_data(data)
            logging.info('data saved successfully')

if __name__ == '__main__':
    main()

以下是成功保存到数据库的界面:

sfqxx 发表于 2023-7-6 18:50:41

{:10_275:}

涛4091 发表于 2023-7-7 11:01:41

{:5_106:}

查看完整版本: 比葫芦画瓢写的电影信息爬取的代码并保存到数据库