1.爬取豆瓣top250書籍 結果 2.把評分為9.0的書籍保存到book_out.csv文件中 ...
1.爬取豆瓣top250書籍
import requests import json import csv from bs4 import BeautifulSoup books = []
def book_name(url): res = requests.get(url) html = res.text soup = BeautifulSoup(html, 'html.parser') items = soup.find(class_="grid-16-8 clearfix").find(class_="indent").find_all('table') for i in items: book = [] title = i.find(class_="pl2").find('a') book.append('《' + title.text.replace(' ', '').replace('\n', '') + '》') star = i.find(class_="star clearfix").find(class_="rating_nums") book.append(star.text + '分') try: brief = i.find(class_="quote").find(class_="inq") except AttributeError: book.append('”暫無簡介“') else: book.append(brief.text) link = i.find(class_="pl2").find('a')['href'] book.append(link) global books books.append(book) print(book) try: next = soup.find(class_="paginator").find(class_="next").find('a')['href'] # 翻到最後一頁 except TypeError: return 0 else: return next next = 'https://book.douban.com/top250?start=0&filter=' count = 0 while next != 0: count += 1 next = book_name(next) print('-----------以上是第' + str(count) + '頁的內容-----------') csv_file = open('D:/top250_books.csv', 'w', newline='', encoding='utf-8') w = csv.writer(csv_file) w.writerow(['書名', '評分', '簡介', '鏈接']) for b in books: w.writerow(b)
結果
2.把評分為9.0的書籍保存到book_out.csv文件中
''' 1.爬取豆瓣評分排行前250本書,保存為top250.csv 2.讀取top250.csv文件,把評分為9.0以上的書籍保存到另外一個csv文件中 ''' import csv #打開的時候必須用encoding='utf-8',否則報錯 with open('top250.csv', encoding='utf-8') as rf: reader = csv.reader(rf) #讀取頭部 headers = next(reader) with open('books_out.csv', 'w', encoding='utf-8') as wf: writer = csv.writer(wf) #把頭部信息寫進去 writer.writerow(headers) for book in reader: #獲取評分 score = book[1] #把評分大於9.0的過濾出來 if score and float(score) >= 9.0: writer.writerow(book)