|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- from bs4 import BeautifulSoup
- import requests
- import time
- headers = {
- 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36'
- }
- def judgment_sex(class_name):
- if class_name == ['member_icol']:
- return '女'
- else:
- return '男'
- def get_links(url):
- wb_data = requests.get(url,headers=headers)
- soup = BeautifulSoup(wb_data.text,'lxml')
- links = soup.select('#page_list > ul > li > a')
- for link in links:
- href = link.get("href")
- get_into(href)
- def get_into(url):
- wb_data = requests.get(url, headers=headers)
- soup = BeautifulSoup(wb_data.text, 'lxml')
- tittles = soup.select('div.pho_info > h4')
- addresses = soup.select('span.pr5')
- prices = soup.select('#pricePart > div_day1 > span')
- imgs = soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > a >img')
- names = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > a')
- sexs = soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > div')
- for tittle,address,price,img,name,sex in zip(tittles,addresses,prices,imgs,names,sexs):
- data = {
- 'tittle':tittle.get_text().strip(),
- 'address':address.get_text().strip(),
- 'price':price.get_text().strip(),
- 'img':img.get("src"),
- 'name':name.get_text().strip(),
- 'sex':judgment_sex(sex.get("class"))
- }
- print(data)
- if __name__ == '__main__':
- urls = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(number) for number in range(1,14)]
- for single_url in urls:
- get_links(single_url)
- time.sleep(2)
复制代码 |
-
|