python 爬取貓眼電影top100數據

本文轉載自查看原文 2019-11-07 16:04 1697 Python

最近有爬蟲相關的需求，所以上B站找了個視頻（鏈接在文末）看了一下，做了一個小程序出來，大體上沒有修改，只是在最后的存儲上，由txt換成了excel。

簡要需求：爬蟲爬取貓眼電影TOP100榜單數據
使用語言：python
工具：PyCharm
涉及庫：requests、re、openpyxl(高版本excel操作庫)

實現代碼

# -*- coding: utf-8 -*-
# @Author  : yocichen
# @Email   : yocichen@126.com
# @File    : maoyan100.py
# @Software: PyCharm
# @Time    : 2019
# @UpdateTime : 2020/4/26

import requests
from requests import RequestException
import re
import openpyxl
import traceback

# Get page's html by requests module
def get_one_page(url):
    try:
        headers = {
            'user-agent': 'Mozilla / 5.0(Windows NT 10.0; WOW64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 53.0.2785.104Safari / 537.36Core / 1.53.4882.400QQBrowser / 9.7.13059.400'
        }
        # Sometimes, the proxies need to be replaced.
        # You can get them by accessing https://www.kuaidaili.com/free/inha/
        proxies = {
            'http': '60.190.250.120:8080'
        }
        # use headers to avoid 403 Forbidden Error(reject spider)
        response = requests.get(url, headers=headers, proxies=proxies)
        if response.status_code == 200 :
            return response.text
        return None
    except RequestException:
        traceback.print_exc()
        return None

# Get useful info from html of a page by re module
def parse_one_page(html):
    try:
        pattern = re.compile('<dd>.*?board-index.*?>(\d+)<.*?<a.*?title="(.*?)"'
                             +'.*?data-src="(.*?)".*?</a>.*?star">[\\s]*(.*?)[\\n][\\s]*</p>.*?'
                             +'releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?'
                             +'fraction">(.*?)</i>.*?</dd>', re.S)
        items = re.findall(pattern, html)
        return items
    except Exception:
        traceback.print_exc()
        return []

# Main call function
def main(url):
    page_html = get_one_page(url)
    parse_res = parse_one_page(page_html)
    return parse_res

# Write the useful info in excel(*.xlsx file)
def write_excel_xlsx(items):
    wb = openpyxl.Workbook()
    ws = wb.active
    rows = len(items)
    cols = len(items[0])
    # First, write col's title.
    ws.cell(1, 1).value = '編號'
    ws.cell(1, 2).value = '片名'
    ws.cell(1, 3).value = '宣傳圖片'
    ws.cell(1, 4).value = '主演'
    ws.cell(1, 5).value = '上映時間'
    ws.cell(1, 6).value = '評分'
    # Write film's info
    for i in range(0, rows):
        for j in range(0, cols):
            if j != 5:
                ws.cell(i+2, j+1).value = items[i][j]
            else:
                ws.cell(i+2, j+1).value = items[i][j]+items[i][j+1]
                break
    # Save the work book as *.xlsx
    wb.save('maoyan_top100.xlsx')

if __name__ == '__main__':
    print('spider working...')
    res = []
    url = 'https://maoyan.com/board/4?'
    for i in range(0, 10):
        if i == 0:
            res = main(url)
        else:
            newUrl = url+'offset='+str(i*10)
            res.extend(main(newUrl))
    print('writing into excel...')
    write_excel_xlsx(res)
    print('work done!\nNote: the data is in the current directory.')