[콩잎] 댓글을 기어오르다(영화평론, 서평)

0x00 선언

0x01 영화 평론

1.단평

import requests
from urllib.parse import urlencode
import re
import csv
import time


#         
def get_one(num):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3724.8 Safari/537.36'

    }
    params = {
        'start': str(num),
        'limit': '20',
        'sort': 'new_score',
        'status': 'P',
        'percent_type': ''
    }
    base_url = 'https://movie.douban.com/subject/20444530/comments?'#          20444530    
    url = base_url + urlencode(params)
    print("    ：" + url)
    try:
        response = requests.get(url, headers=headers, timeout=10)
        if response.status_code == 200:
            return response.text
    except EOFError as e:
        print(e)
        return None


#       
def parse_page(html):
    info = []
    patten1 = re.compile(
        r'
.*?(.*?).*?.*?.*?
(.*?)
.*?
',
        re.S)
    datas = re.findall(patten1, html)
    print(datas)
    for data in datas:
        comic = {}
        comic['User'] = data[0].strip()
        comic['Time'] = data[1].strip()
        comic['Comment'] = data[2].strip().split()
        info.append(comic)
    return info


#               
def write_to_file(info):
    with open('《       》  .csv', 'a', newline='') as f:
        fieldnames = ['User', 'Time', 'Comment']
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        
        writer.writeheader()
        try:
            writer.writerows(info)
        except:
            pass


#     
def main():
    for i in range(10):
        html = get_one(i * 20)
        datas = parse_page(html)
        write_to_file(datas)
        print('      。')  #          
        time.sleep(1)  #          


if __name__ == '__main__':
    main()

2.장평

0x02 서평

1.단평

import requests
from urllib.parse import urlencode
import re
import csv
import time


#         
def get_one(num):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3724.8 Safari/537.36'

    }
    params = {
        'p': str(num)
    }
    base_url = 'https://book.douban.com/subject/24838578/comments/hot?' #       ，  24838578   
    url = base_url + urlencode(params)
    print("    ：" + url)
    try:
        response = requests.get(url, headers=headers, timeout=10)
        if response.status_code == 200:
            return response.text
    except EOFError as e:
        print(e)
        return None


#       
def parse_page(html):
    info = []
    patten1 = re.compile(
        r'
.*?.*?(.*?).*?.*?
(.*?)
.*?
',        re.S)
    datas = re.findall(patten1, html)
    #print(datas)
    for data in datas:
        comic = {}
        comic['User'] = data[0].strip()
        # comic['Time'] = data[1].strip()
        comic['Comment'] = data[1].strip().split()
        #print(comic)
        info.append(comic)
    return info


#          
def write_to_file(info):
    with open('《       》  .csv', 'a', newline='') as f:
        fieldnames = ['User', 'Comment']
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        writer.writeheader()
        try:
            writer.writerows(info)
        except:
            pass


#     
def main():
    for i in range(0,100):
        html = get_one(i)
        datas = parse_page(html)
        write_to_file(datas)
        print('      。')  #          
        #time.sleep(1)  #          


if __name__ == '__main__':
    main()

2.장평