Reptile Day03

import requests

respones=requests.get(url='http://www.baidu.com')
respones.encoding='UTF-8'
print(respones.text)

with open ('badui.html','w',encoding='UTF-8')as f:
    f.write (respones.text) # climb baidu home page written in HTML

Today's study:

Climb watercress

https://movie.douban.com/top250?start=0&filter=
https://movie.douban.com/top250?start=25&filter=
https://movie.douban.com/top250?start=50&filter=

A Request to Send
 2 . Analytical data
 3 . Save the data
 '' '
import requests
import re

# Reptile three-part song
# 1 sends a request
def get_page(base_url):
    response = requests.get(base_url)
    return response

# 2. parse text
def parse_index(text):

    res = re.findall('<div class="item">.*?<em class="">(.*?)</em>.*?<a href="(.*?)">.*?<span class="title">(.*?)</span>.*?导演:(.*?)</p>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价</span>.*?<span class="inq">(.*?)</span>', text, re.S)
    # print(res)
    return res

# 3. Save data
def save_data(data):
    with open('douban.txt', 'a', encoding='utf-8') as f:
        f.write(data)

# Main + Enter key
if __name__ == '__main__':
    # A = 10
    # base_url = 'https://movie.douban.com/top250?start={}&filter='.format(num)

    a = 0
    for line in range(10):
        base_url = f'https://movie.douban.com/top250?start={num}&filter='
        a = + 25
        print(base_url)

        # 1 sends a request, the calling function
        response = get_page(base_url)

        # 2. parse text
        movie_list = parse_index(response.text)

        # 3. Save data
        # Formatted data
        for movie in movie_list:
            # print(movie)

            # Decompression assignment
            Ranked # movie, movies url, film name, director - starring - the type of movie scores, number of reviews, film synopsis
            v_top, v_url, v_name, v_daoyan, v_point, v_num, v_desc = movie
            # v_top = movie[0]
            # v_url = movie[1]
            moive_content = f'''
            Movie Ranking: {v_top}
            Film url: {v_url}
            Movie Name: {v_name}
            Director Starring: {v_daoyan}
            Movie rating: {v_point}
            Number of Evaluation: {v_num}
            Movie Synopsis: {v_desc}
            \n
            '''

            print(moive_content)

            # save data
            save_data(moive_content)