python解析网页数据BeautifulSoup和xpath

前言：requests请求并获取数据后，解析数据通常用两种方法（BeautifulSoup和xpath），下面以某房chan数据有例子，分别使用不同的方法解析数据。

一、xpath方法：

from lxml import etreee = etree.HTML(resp.text)names = [n.strip() for n in e.xpath("//div[@class='nlcd_name']/a/text()")]

二、BeautifulSoup方法：

from bs4 import BeautifulSoup bs = BeautifulSoup(resp.text, 'html.parser') nl_con = bs.find("div", class_='nl_con clearfix') li_list = nl_con.find_all("li") lst = [] for item in li_list: names = item.find('div', class_="nlcd_name")

个人比较喜欢用BeautifulSoup方法，一是BeautifulSoup方法接触比较早，而且BeautifulSoup方法可以跟re方法结合使用。非常灵活方便。

详细实例：

import requestsfrom lxml import etreeimport pandasheaders = { "User-Agent": "Mozilla/5.0(Windows NT 6.1;WOW64) AppleWebKit/537.36(KABUL, like Gecko) " "Chrome/86.0.4240.198Safari/537.36 "}for i in range(1, 2): url = f"https://newhouse.fang.com/house/s/b9{i}" resp = requests.get(url, headers=headers) resp.encoding = resp.apparent_encoding e = etree.HTML(resp.text) names = [n.strip() for n in e.xpath("//div[@class='nlcd_name']/a/text()")] address = e.xpath("//div[@class='address']/a/@title") prices = [d.xpath('string(.)').strip() for d in e.xpath("//div[@class='nhouse_price']")] fangyuan = [n.strip() for n in e.xpath("//div[@class='fangyuan']/span/text()")] data = [] for n, a, p, f in zip(names, address, prices, fangyuan): data.append([n, a, p ,f])for i in data: print(i)df = pandas.DataFrame(data, columns=['小区名', '地址', '单价', '是否在售'])print(df)

import requestsfrom bs4 import BeautifulSoupimport reimport pandasheaders = { "User-Agent": "Mozilla/5.0(Windows NT 6.1;WOW64) AppleWebKit/537.36(KABUL, like Gecko) " "Chrome/86.0.4240.198Safari/537.36 "}for i in range(1, 2): url = f"https://newhouse.fang.com/house/s/b9{i}" resp = requests.get(url, headers=headers) resp.encoding = resp.apparent_encoding bs = BeautifulSoup(resp.text, 'html.parser') nl_con = bs.find("div", class_='nl_con clearfix') li_list = nl_con.find_all("li") lst = [] for item in li_list: names = item.find('div', class_="nlcd_name") names = names.find('a').text.strip() address = item.find('div', class_="address") address = address.find('a')['title'] prices = item.find('div', class_="nhouse_price").text.strip() house_tyep = item.find('div', class_='house_type clearfix').text.replace('\n', ' ').replace('\r', '').replace(" ", "") house_tyep = re.sub(r'[\s]+', '', house_tyep) fangyuan = item.find('div', class_='fangyuan').text.replace('\n', ' ').replace('\r', '').replace(" ", "") fangyuan = re.sub(r'[\s]+', '', fangyuan) # print(names, address, prices, house_tyep, fangyuan) # break lst.append([names, address, prices, house_tyep, fangyuan])# for i in lst:# print(i)df = pandas.DataFrame(lst, columns=['小区名', '地址', '户型信息', '单价', '是否在售'])print(df)