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(' ', '') + '》')
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) + '頁的内容-----------')
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', '連結'])
for b in books:
w.writerow(b)
結果
2.把評分為9.0的書籍儲存到book_out.csv檔案中
'''
1.爬取豆瓣評分排行前250本書,儲存為top250.csv
2.讀取top250.csv檔案，把評分為9.0以上的書籍儲存到另外一個csv檔案中
'''
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)
#把頭部資訊寫進去
writer.writerow(headers)
for book in reader:
#擷取評分
score = book[1]
#把評分大于9.0的過濾出來
if score and float(score) >= 9.0:
writer.writerow(book)
總結
以上所述是小編給大家介紹的python讀寫csv檔案的方法,希望對大家有所幫助，如果大家有任何疑問請給我留言，小編會及時回複大家的。在此也非常感謝大家對腳本之家網站的支援！
如果你覺得本文對你有幫助，歡迎轉載，煩請注明出處，謝謝！