Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit b09f9f7

Browse files
创建目录
1 parent 0f969a6 commit b09f9f7

File tree

3 files changed

+94
-0
lines changed

3 files changed

+94
-0
lines changed

‎wuya/README.md

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
# Python 代码实例
2+
3+
- [jdSignin](https://github.com/JustDoPython/python-examples/tree/master/wuya/jdSignin) : 3分钟写一个脚本,每天定时薅东哥羊毛
4+
- [shRent_1](https://github.com/JustDoPython/python-examples/tree/master/wuya/shRent_1) : 为了在上海租房,我用python连夜爬了20000多条房源信息...
5+
6+
---
7+
8+
从小白到工程师的学习之路
9+
10+
关注公众号:python 技术,回复"python"一起学习交流
11+
12+
![](http://favorites.ren/assets/images/python.jpg)

‎wuya/jdSignin/jd_sign.py

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
#pt_key=AAJi2BVXADDKWR6SHbo_ARE3SS6Bv7y-nKo0aWKLQjiYCcmreYfTUHN15o-nlRdh2M3iwV5kYv8; pt_pin=zhongulou;
2+
import requests
3+
4+
pt_key="替换为自己的pt_key"
5+
pt_pin="替换为自己的pt_pin"
6+
cookie="pt_key={}; pt_pin={}".format(pt_key, pt_pin)
7+
url = "https://api.m.jd.com/client.action?functionId=signBeanAct&body=%7B%22fp%22%3A%22-1%22%2C%22shshshfp%22%3A%22-1%22%2C%22shshshfpa%22%3A%22-1%22%2C%22referUrl%22%3A%22-1%22%2C%22userAgent%22%3A%22-1%22%2C%22jda%22%3A%22-1%22%2C%22rnVersion%22%3A%223.9%22%7D&appid=ld";
8+
headers = {
9+
"Content-Type":"application/x-www-form-urlencoded; charset=UTF-8",
10+
"User-Agent": "okhttp/3.12.1;jdmall;android;version/10.3.4;build/92451;",
11+
"Cookie": cookie
12+
}
13+
14+
response = requests.post(url=url, headers=headers)
15+
print(response.text)
16+
17+
res = response.json()
18+
returnMes = ""
19+
20+
if(res.get("errorMessage")==None):
21+
returnMes = "签到成功!"
22+
else:
23+
returnMes = "签到失败".format(res.get("errorMessage"))
24+
25+
requests.get("https://sctapi.ftqq.com/这里填写你个人的SendKey.send?title={}".format(returnMes))

‎wuya/shRent_1/shRent_1.py

Lines changed: 57 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,57 @@
1+
#通过某租房网站首页接口爬取租房房源信息
2+
import time, re, csv, requests
3+
import codecs
4+
from bs4 import BeautifulSoup
5+
6+
list=['jingan','xuhui','huangpu','changning','putuo','pudong','baoshan','hongkou','yangpu','minhang','jinshan','jiading','chongming','fengxian','songjiang','qingpu']
7+
print("****处理开始****")
8+
with open(r'..\document\sh.csv', 'wb+')as fp:
9+
fp.write(codecs.BOM_UTF8)
10+
f = open(r'..\document\sh.csv','w+',newline='', encoding='utf-8')
11+
writer = csv.writer(f)
12+
urls = []
13+
14+
for a in list:
15+
urls.append('https://sh.lianjia.com/zufang/{}/pg1rco11/'.format(a))
16+
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.9 Safari/537.36'}
17+
18+
res = requests.get('https://sh.lianjia.com/zufang/{}/pg1rco11/'.format(a), headers=headers)
19+
content = res.text
20+
soup = BeautifulSoup(content, 'html.parser')
21+
page_num = int(soup.find('div', attrs={'class': 'content__pg'}).attrs['data-totalpage'])
22+
for i in range(2,page_num+1):
23+
urls.append('https://sh.lianjia.com/zufang/{}/pg{}rco11/'.format(a,i))
24+
25+
print(urls)
26+
27+
num=1
28+
for url in urls:
29+
print("正在处理第{}页数据...".format(str(num)))
30+
res1 = requests.get(url, headers=headers)
31+
content1 = res1.text
32+
soup1 = BeautifulSoup(content1, 'html.parser')
33+
infos = soup1.find('div', {'class': 'content__list'}).find_all('div', {'class': 'content__list--item'})
34+
35+
for info in infos:
36+
37+
house_url = 'https://sh.lianjia.com' + info.a['href']
38+
title = info.find('p', {'class': 'content__list--item--title'}).find('a').get_text().strip()
39+
group = title.split()[0][3:]
40+
price = info.find('span', {'class': 'content__list--item-price'}).get_text()
41+
tag = info.find('p', {'class': 'content__list--item--bottom oneline'}).get_text()
42+
mixed = info.find('p', {'class': 'content__list--item--des'}).get_text()
43+
mix = re.split(r'/', mixed)
44+
address = mix[0].strip()
45+
area = mix[1].strip()
46+
door_orientation = mix[2].strip()
47+
style = mix[-1].strip()
48+
region = re.split(r'-', address)[0]
49+
writer.writerow((house_url, title, group, price, area, address, door_orientation, style, tag, region))
50+
time.sleep(0)
51+
print("第{}页数据处理完毕,共{}条数据。".format(str(num), len(infos)))
52+
num+=1
53+
54+
55+
f.close()
56+
print("****全部完成****")
57+

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /