猫眼TOP100爬虫代码「持续更新」

你好，悦创。

爬虫网站链接：https://ssr1.scrape.center/page/1，视频回放请联系 AI悦创

代码：

# title
# 地区
# score
# image
# datetime
import re
import requests
from requests.exceptions import RequestException
class MaoYan(object):
    def __init__(self):
        self.headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36",}

    def requests(self, url):
        try:
            response = requests.get(url, headers=self.headers)
            if response.status_code == 200:
                return response.text
            else:
                return "None"
        except RequestException as e:
            return e
    def pattern(self, string):
        img_lst = re.findall(r'<img.*?data-v-7f856186.*?src="(.*?)".*?cover.*?>', string, re.S|re.I)
        title = r'<h2.*?class="m-b-sm">(.*?)</h2>'
        # pattern = r'<div.*?data-v-7f856186.*?<a.*?href="(.*?)".*?img.*?src="(.*?)"cover.*?>'
        pattern = r'<div.*?data-v-7f856186.*?el-row.*?<a.*?href="(.*?)".*?' \
                  r'<img.*?src="(.*?)".*?cover">' \
                  r'.*?data-v-7f856186.*?h2.*?data-v-7f856186.*?>(.*?)</h2>' \
                  r'.*?categories.*?button.*?type="button".*?span>(.*?)</span>' \
                  r'.*?div.*?data-v-7f856186.*?span.*?>(.*?)</span>' \
                  r'.*?<span.*?>(.*?)</span>' \
                  r'.*?<span.*?>(.*?)</span>' \
                  r'.*?data-v-7f856186.*?<span.*?>(.*?)</span>' \
                  r'.*?data-v-7f856186.*?p.*?score.*?>(.*?)</p>'
        return re.findall(pattern, string, re.S|re.I)
        # return re.findall('<p.*?data-v-7f856186.*?class="score.*?">(.*?)</p>', string, re.S|re.I)
    def parse(self, content):
        lst = self.pattern(content)
        print(lst)
        print(len(lst))

    def main(self):
        url = "https://ssr1.scrape.center/page/1"
        html = self.requests(url)
        # print(html)
        self.parse(html)

if __name__ == '__main__':
    Crawler = MaoYan()
    Crawler.main()