python爬虫豆瓣电影到csv_python爬虫。豆瓣图书并且存储在本地csv格式

import requests

from lxml import etree

import csv

fp=open("豆瓣.csv",'wt',newline="",encoding="utf-8")

writer=csv.writer(fp)

writer.writerow(('name','author','publish'))

urls=['https://book.douban.com/top250?start={}'.format(str(i)) for i in range(0,250,25)]

headers = {

'User-Agent': 'Mozilla/5.0 (Macintosh;Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko)\

Chrome/52.0.2743.116 Safari/537.36'

}

for url in urls:

html = requests.get(url, headers=headers)

selector=etree.HTML(html.text)

infos=selector.xpath('//tr[@class="item"]')

#infos = selector.xpath('//div[@class ="indent"]/table[@width="100%"]')证明自己是对的

for info in infos:

name=info.xpath('td/div/a/@title')[0]

#name = info.xpath('tr/td[2]/div/a/@title')[0].split(',')[:]证明自己是对的

book_info=info.xpath('td/p/text()')[0]

author=book_info.split('/')[0]

publish=book_info.split('/')[-3]

writer.writerow((name,author,publish))

fp.close()

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！