You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
python/bs4nanningzufang0902.py

105 lines
3.9 KiB

import requests
from bs4 import BeautifulSoup
from openpyxl import Workbook
import time
import random
wb = Workbook() #创建一个workbook
def createSheetObj():
sheet = wb.active #获取当前workbook的第一个worksheet
sheet.title = "58同城" #worksheet的标题
sheet.append(['短租房名称', '短租房链接', '短租房地址', "短租房价格 元/日", "短租房居住人数", "出租类型", "短租房户型", "面积/㎡", "用户评论数", "用户评分","用户满意度"]) # 添加一行表头
return sheet
def getpage1(): #返回网页源码
path = 'nn.html'
htmlfile = open(path, 'r', encoding='utf-8') #打开1.html文件
htmlhandle = htmlfile.read() #返回整个文件
soup = BeautifulSoup(htmlhandle, "lxml") #使用Beautifulsoup解析
#print(soup)
return soup
def getPage(url):
# 伪造身份
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18363'
}
resp = requests.get(url, headers=headers)
print(resp.status_code)
resp.encoding = "utf-8"
html = resp.text
soup = BeautifulSoup(html, "lxml")
return soup
def parsePage():
soup = getpage1()
i = 0
lis = soup.find_all("a", attrs={"class": "ui-house-item-house-wrapper"}) #找到所有li的链接地址
for li in lis:
print("" + str(i) + "")
i = i + 1
house_name = li.find('div',class_='ui-house-item-content-area-title').get_text()
house_href = 'http:' + li.get('href')
house_location = li.find('div',class_='ui-house-item-content-area-introduce2').get_text()
house_price = li.find('span', class_='ui-house-item-price-area-nowprice-price').get_text()
house_unit = li.find('span', class_='ui-house-item-price-area-nowprice-unit').get_text()
z = house_unit.split('/')
if(z[1] == ""):
house_price = int(house_price) // 30
house_person_type_huxing = li.find('div', class_='ui-house-item-content-area-introduce3').get_text()
#合住房间·4室1床·可住1人·7天起租
x = house_person_type_huxing.split('·')
house_type = x[0]
house_huxing = x[1]
house_person = x[2][2] #第三个字
#异常/缺省值处理
try:
house_score_comments = li.find('div', class_='ui-house-item-content-area-introduce1').get_text()
y = house_score_comments.split('/')
house_score = y[0][0] + y[0][1] + y[0][2]
house_comments = y[1][0]
except:
house_score = 0
house_comments =0
try:
house_satisfy = li.find('div', class_='ui-house-item-pic-degreeofsatisfaction-number').get_text()
s = house_satisfy.split(':')
house_satisfy_num = s[1]
except:
house_satisfy_num = 0
try:
soup1 = getPage(house_href)
house_square = soup1.find_all('div',class_='desc')[2].get_text()
#print(house_square)
house_square = house_square.strip('')
#print(house_square)
except:
house_square = 0
print(house_name,house_href,house_location,house_price,
house_person,house_type,house_huxing,house_square,house_comments,house_score,house_satisfy_num)
sheet.append([house_name,house_href,house_location,house_price,
house_person,house_type,house_huxing,house_square,house_comments,house_score,house_satisfy_num])
time.sleep(random.random() * 3) #模拟人的行为
if (i > 2000):
print("爬取结束")
break
#wb.save("nanning.xlsx") #将最终的结果导出到本地文件
#wb.save("nanning.csv")
wb.save("nanning.json")
sheet = createSheetObj()
parsePage()