使用selenium爬取猫Y电影Top100榜单

selenium_maoyan_com.py

import json
import re
import time

import requests


def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)' 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.100 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    return None


def parse_one_page(html):
    pattern = re.compile(
        '<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star.*?(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?(.*?)</i>.*?</dd>',
        re.S
    )
    items = re.findall(pattern, html)
    # print(items)
    # print('__________________________________')
    for item in items:
        maoyan_com_dict = {
            'index': item[0],
            'image': item[1],
            'title': item[2].strip(),
            'actor': item[3].strip()[3:] if len(item[3]) > 3 else '',
            'time': item[4].strip()[5:] if len(item[4]) > 5 else '',
            'score': item[5].strip() + item[6].strip()
        }
        yield maoyan_com_dict


def write_to_file(content):
    with open('../maoyan_com_result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')


def main(offset):
    url = 'https://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    # print('__________________________________')
    # parse_one_page(html)
    # print('__________________________________')
    for item in parse_one_page(html):
        write_to_file(item)


if __name__ == '__main__':
    for i in range(10):
        main(offset=i*10)
        time.sleep(1)

selenium_maoyan_com.py

标签：maoyan,selenium,爬取,item,html,com,strip,Top100,page
来源： https://www.cnblogs.com/Harold-Hua/p/15169292.html