Python fun crawler crawling love Qiyi popular movies

'''
Steps
1, get the url content

2,css select the content of its choice

3, save the data you need

'''
# Import the packages needed for the crawler
import requests
from bs4 import BeautifulSoup
#requests and BeautifulSoup for parsing web pages
import time
#Set the access time to the web page, to prevent their IP access to the more restricted denial of access
import re
class Position():
 
    def __init__(self,position_name,position_require,):#Build object properties
        self.position_name=position_name
        self.position_require=position_require
 
    def __str__(self):
        return '%s%s/n'%(self.position_name,self.position_require)# Overloaded methods to change input variables to string form
 
class Aiqiyi():
    def iqiyi(self,url):
        head= {
            'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36 Edg/87.0.664.47"
        }  # Simulated server header
        html = (url,headers=head)
        #headers=hard Make the script accessible as a browser, there are some URLs that are forbidden by python's anti-crawl mechanism, this is one of them
        soup = BeautifulSoup(, 'lxml', from_encoding='utf-8')  # BeautifulSoup to view web pages
        soupl = (".qy-list-wrap")  # Find tags, use css selector, select the data you need to select the first content of the page (tags to find the only, find id good, if not consider other tags such as class)
        results = []  # Create a list to store the data
        for e in soupl:
            biao = ('.qy-mod-li')  # Conduct secondary screening
            for h in biao:
                p=Position(h.select_one('.qy-mod-link-wrap').get_text(strip=True),
                       h.select_one('.title-wrap').get_text(strip=True))# Call class conversion (continue filtering three times to select what you need)
                (p)
        return results  # Return to content
 
    def address(self,url):
        # Save URL
        head = {
            'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36 Edg/87.0.664.47"
        }  # Simulated server headers
        html = (url, headers=head)
        soup = BeautifulSoup(, 'lxml', from_encoding='utf-8')  # BeautifulSoup to view web pages
        alist = ('div', class_='qy-list-wrap').find_all("a")  # Find the a tag under the div block module
        ls=[]
        for i in alist:
            (('href'))
 
        return ls
 
 
 
if __name__ == '__main__':
    (2)
    #Set up 2-second visits
    a=Aiqiyi()
    url = "/www/1/-------------"
    with open(file='e:/exercise.txt ', mode='a+') as f:  # e:/exercise.txt is a new file created on my computer, a+ adds to the content but does not overwrite it.
         for item in (url):
             line = f'{item.position_name}\t{item.position_require}\n'
             (line)  # Adoption of methodology
             print("Download complete.")
    with open(file='e:/address.txt ', mode='a+') as f:  # e:/exercise.txt is a new file created on my computer, a+ adds to the content but does not overwrite it.
        for item in (url):
            line=f'https{item}\n'
            (line)  # Adoption of methodology
            print("Download complete.")