Created
July 5, 2018 04:15
-
-
Save pandada8/5a8a49f23878f4c20914479933bfcc5e to your computer and use it in GitHub Desktop.
简单的自如爬虫
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pymongo | |
import requests | |
import sys | |
col = pymongo.MongoClient().get_database('ziroom').get_collection('room') | |
r = requests.session() | |
r.headers['User-Agent'] = 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1' | |
def get_list_of_room(name): | |
page = 1 | |
while True: | |
data = r.get("http://m.ziroom.com/v7/room/list.json", params={ "city_code": "110000", "page": page, "keywords": name}).json() | |
if len(data['data']['rooms']): | |
yield from data['data']['rooms'] | |
page += 1 | |
else: | |
break | |
def fetch_detail(id): | |
if col.find_one({"_id": id}): | |
return | |
data = r.get('http://m.ziroom.com/v7/room/detail.json', params={'city_code': "110000", 'id': id}).json()['data'] | |
data['_id'] = data['id'] | |
col.insert(data) | |
print(data['subway_primary'], data['price'], data['price_unit'], data['id']) | |
def main(): | |
for room in get_list_of_room(sys.argv[1]): | |
fetch_detail(room['id']) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment