以下是为您整理出来关于【爬虫 豆瓣】合集内容，如果觉得还不错，请帮忙转发推荐。
单纯地练习一下xpath 1import requests2from lxml import etree3 4 5def get_url(url):6 html = requests.get(url)7return html.text8 910def parse_html(html): 11 informations = [] 12 html_element = etree.HTML(html) 13 ul = html_element.xpath(‘//ul[@class="lists"]‘)[0] 14for li in ul: 15 href = li.xpath(‘.//li[@class="poster"]/a/@href‘) 16 title = li.xpath(‘normalize-sp...
# —*- coding = utf-8 -*- # Author : tian # 时间 ： 2021/4/12 9:36from bs4 import BeautifulSoup # 网页解析，获取数据 import re # 正则表达式，进行文字匹配 import urllib.request, urllib.error # 指定url,获取网页数据 import xlwt # 进行excel操作 import sqlite3 # 进行Sqlite数据库操作def main():baseurl = "https://movie.douban.com/top250?start="# 1. 爬取网页datalist = getData(baseurl)savepath = "top2...
1作业 此作业至今未运行出结果，有待验证# 找规律 # 基本思路获取每个页面的url，通过params函数可获得 # <a href="?start=0&filter=">1</a> # <a href="?start=25&filter=">2</a> import requests import re url=https://movie.douban.com/top250 headers={User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36 } page_number=0 while pag...
1 import requests2 import json3 import csv4 5 6 class DoubantvSpider:7 def __init__(self):8 # self.proxies = {"http":"http://125.123.152.81:3000"}9 self.url = "https://movie.douban.com/j/search_subjects?type=tv&tag=%E5%9B%BD%E4%BA%A7%E5%89%A7&sort=rank&page_limit=20&page_start={}" # 手机模式下国产剧请求网址 10 self.headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; ...