实现功能
在win10操作系统环境下,基于python3.10解释器,爬取豆瓣电影Top250的相关信息并将爬取的信息写入Excel表中。
实现代码
采集爬取模块:scraper.py
python
import requests
from bs4 import BeautifulSoup
from typing import List
import re
class Movie:
def __init__(self, detail_link: str, image_link: str, chinese_name: str, foreign_name: str, rating: float, review_count: int, overview: str, director: str, actors: str, year: int, region: str, category: str):
self.detail_link = detail_link
self.image_link = image_link
self.chinese_name = chinese_name
self.foreign_name = foreign_name
self.rating = rating
self.review_count = review_count
self.overview = overview
self.director = director
self.actors = actors
self.year = year
self.region = region
self.category = category
class Scraper:
def __init__(self, base_url: str):
self.base_url = base_url
self.movies = []
def scrape(self) -> List[Movie]:
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
"Cookie": "bid=m9sDMeuTWp4; ap_v=0,6.0; _pk_id.100001.4cf6=d6615bd2530852c6.1700447648.; _pk_ses.100001.4cf6=1; __utma=30149280.633232779.1700447649.1700447649.1700447649.1; __utmb=30149280.0.10.1700447649; __utmc=30149280; __utmz=30149280.1700447649.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); __utma=223695111.1435231277.1700447649.1700447649.1700447649.1; __utmb=223695111.0.10.1700447649; __utmc=223695111; __utmz=223695111.1700447649.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); _cc_id=748927837a892b664c1f1ab42fbe510a; panoramaId_expiry=1700534054317; panoramaId=18a92c0e9b136f927d0f0871ae33a9fb927a9d987bb8aa39557c58077684bc2c; panoramaIdType=panoDevice; _pbjs_userid_consent_data=3524755945110770; __gads=ID=7617c807b66fd695:T=1700447653:RT=1700448285:S=ALNI_MY0jxMNVX0GooLXe8dtdh74vfdLvQ; __gpi=UID=00000cdbaaf33934:T=1700447653:RT=1700448285:S=ALNI_MYekZkuVr46VHfZjhuhdX2kpLxOkw; cto_bundle=xIP-n181MjZFSVBGdlMlMkJEY3hvY3dycER1QjhISjdGU2dzOWxWZUFSMmNZd25VQ1Y0REdtaXZPdTh2aEJGUCUyQlo3WjVETzVNc2VUSFR3dHFXQVRRZU1ZejdOMXk5RDM4VjV1WkJsRWVXd1dQdjRvRE1JQjhEVkJQUVEyV0M1dlgzVkFBclZDTnJWM1g3MWZERDltRFR1UDZZNXp3JTNEJTNE; cto_bidid=vr7nBV8lMkZGJTJCOGVQWjhWREJUelpJYm1UdFBWaWd5bk9WT1JCdyUyRjlpN1duSWFZd3JPR2dkdmh1Q2tNa3NJa25rQTExSFlPM1p2YzdpT1U2cDE5UUowU3p1VHk3YkhVWWw4aFBmUExiZmtZdWtPS3U4byUzRA; cto_dna_bundle=14GGU181MjZFSVBGdlMlMkJEY3hvY3dycER1QiUyQmxhTVFwSEdNWHZ6OE5MZ2olMkJQbjlyODR2SWtIJTJCUGZmYm40Z3p5b1AxbSUyRkJKVDBVUVlXbGE1ZWRQeVUlMkJmeTR5dyUzRCUzRA",
}
for i in range(0, 10): # 左闭右开
self.url = self.base_url + str(i * 25) # 字符串的拼接,调用获取页面信息的函数,10次(一共10页)
response = requests.get(self.url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
movie_elements = soup.find_all('div', class_='item')
for movie_element in movie_elements:
detail_link = movie_element.find('a')['href']
image_link = movie_element.find('img')['src']
title_element = movie_element.find('div', class_='hd')
chinese_name = title_element.find('span', class_='title').text
foreign_name = title_element.find('span', class_='other').text.strip()[2:]
rating = float(movie_element.find('span', class_='rating_num').text)
# review_count = int(movie_element.find('span', class_='rating_people').find('span').text)
review_count = re.findall(re.compile(r'<span>(\d*)人评价</span>'), str(movie_element))[0]
overview = movie_element.find('span', class_='inq').text if movie_element.find('span', class_='inq') else ''
info_text = movie_element.find('div', class_='bd').find('p').text
director = info_text.split('导演: ')[1].split(' ')[0]
actors = info_text.split('主演: ')[1].split(' ')[0] if '主演: ' in info_text else ''
year_region_category = info_text.split('\n')[-2].strip().split('/')
try:
year = int(year_region_category[0].strip())
except ValueError as e:
print(e)
year = None
region = year_region_category[-2].strip()
category = year_region_category[-1].strip()
movie = Movie(detail_link, image_link, chinese_name, foreign_name, rating, review_count, overview, director, actors, year, region, category)
self.movies.append(movie)
return self.movies
写入文件模块:writer.py
python
import pandas as pd
from typing import List
from openpyxl import Workbook
from openpyxl.utils.dataframe import dataframe_to_rows
from scraper import Movie # Import the Movie class
class Writer:
def __init__(self, file_path: str):
self.file_path = file_path
def write(self, movies: List[Movie]): # Specify the type of objects in the list
data = {
'Detail Link': [movie.detail_link for movie in movies],
'Image Link': [movie.image_link for movie in movies],
'Chinese Name': [movie.chinese_name for movie in movies],
'Foreign Name': [movie.foreign_name for movie in movies],
'Rating': [movie.rating for movie in movies],
'Review Count': [movie.review_count for movie in movies],
'Overview': [movie.overview for movie in movies],
'Director': [movie.director for movie in movies],
'Actors': [movie.actors for movie in movies],
'Year': [movie.year for movie in movies],
'Region': [movie.region for movie in movies],
'Category': [movie.category for movie in movies]
}
df = pd.DataFrame(data)
wb = Workbook()
ws = wb.active
for r in dataframe_to_rows(df, index=False, header=True):
ws.append(r)
wb.save(self.file_path)
主程序模块:main.py
python
from scraper import Scraper, Movie
from writer import Writer
def main():
# base_url = 'https://movie.douban.com/top250'
base_url = "https://movie.douban.com/top250?start="
file_path = 'douban_movies.xlsx'
# Initialize scraper and scrape data
scraper = Scraper(base_url)
movies = scraper.scrape()
# Initialize writer and write data to file
writer = Writer(file_path)
writer.write(movies)
if __name__ == '__main__':
main()
实现效果
写在后面
本人读研期间发表5篇SCI数据挖掘相关论文,现在某研究院从事数据算法相关科研工作,对Python有一定认知和理解,会结合自身科研实践经历不定期分享关于python、机器学习、深度学习等基础知识与应用案例。
致力于只做原创,以最简单的方式理解和学习,关注我一起交流成长。
1、邀请三个朋友关注本订阅号或2、分享/在看任意订阅号的三篇文章即可在后台联系我获取相关数据集和源码。
2、关注"数据杂坛"公众号,点击"领资料"即可免费领取资料书籍。
3、如果对本文有疑问,或者有论文指导的相关需求,点击"联系我"添加作者微信直接交流。