51无聊谢了个爬虫玩
python写这类小东西真的很方便
__author__='LeoKim' from bs4 import BeautifulSoup import re import urllib.request, urllib.parse, http.cookiejar import json import time import pymysql conn=pymysql.connect(host='localhost',user='root',passwd='superhero',db='python_test',port=3306,charset='utf8') cur=conn.cursor()#获取一个游标 #通过链接获取每页的小区名 def getVillage(url): cj = http.cookiejar.CookieJar() opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj)) opener.addheaders = [('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36'), ('Cookie', 'select_city=320100; lianjia_uuid=c73af582-9ed7-42ed-9738-bbd4688c67e0; UM_distinctid=15bb9f33ca387c-0ac15874ad5d0d-6a11157a-1fa400-15bb9f33ca4a02; _jzqckmp=1; all-lj=c28812af28ef34a41ba2474a2b5c52c2; _jzqx=1.1493473537.1493544561.2.jzqsr=nj%2Elianjia%2Ecom|jzqct=/ershoufang/gulou/.jzqsr=nj%2Elianjia%2Ecom|jzqct=/xiaoqu/pg1/; _gat=1; _gat_past=1; _gat_global=1; _gat_new_global=1; _gat_dianpu_agent=1; _smt_uid=59049861.8870a59; CNZZDATA1253492138=835595246-1493470448-null%7C1493541950; CNZZDATA1254525948=1922726511-1493470772-null%7C1493540995; CNZZDATA1255633284=630946367-1493469955-null%7C1493543402; CNZZDATA1255604082=270979082-1493468920-null%7C1493544528; _qzja=1.1520598967.1493473405458.1493480837509.1493544561423.1493544849473.1493544851953.0.0.0.29.3; _qzjb=1.1493544561423.10.0.0.0; _qzjc=1; _qzjto=10.1.0; _jzqa=1.2414222906473966000.1493473537.1493480838.1493544561.3; _jzqc=1; _jzqb=1.10.10.1493544561.1; _ga=GA1.2.1108117219.1493473408; _gid=GA1.2.2091828031.1493544853; lianjia_ssid=5c8ebd96-81f4-4430-bfda-6d941fcb8663')] urllib.request.install_opener(opener) html_bytes = urllib.request.urlopen(url).read() html_string = html_bytes.decode('utf-8') return html_string def start(start_url): html_doc = getVillage(start_url) soup = BeautifulSoup(html_doc, 'html.parser') #获取所有页数和现在页数 totalPageNoDiv=soup.find("div","house-lst-page-box") Page = eval(totalPageNoDiv.attrs['page-data']) totalPageNo = Page['totalPage'] curPage = Page['curPage'] print('当前正在抓取第'+str(curPage)+'页,共'+str(totalPageNo)+'页.') #获取小区内容 divs = soup.find_all("div","title") for div in divs: a_tag = div.find("a",target="_blank") if(a_tag): #插入数据库 sql = "INSERT INTO `village` (`name`) VALUES (%s)" cur.execute(sql, (a_tag.string)) curPage = curPage + 1; if(totalPageNo == curPage-1): print('执行完毕.') else: time.sleep(10) start_url = "http://nj.lianjia.com/xiaoqu/pg"+str(curPage) start(start_url) totalPageNo=1 curPage=1 start_url = "http://nj.lianjia.com/xiaoqu/pg"+str(curPage) start(start_url) cur.close()#关闭游标 conn.close()#释放数据库资源
__author__='LeoKim' from bs4 import BeautifulSoup import pymysql import urllib.request, urllib.parse, http.cookiejar from urllib import parse import pymysql conn=pymysql.connect(host='localhost',user='root',passwd='superhero',db='python_test',port=3306,charset='utf8') cur=conn.cursor()#获取一个游标 def getgeohash(keyword): key={ 'keyword':keyword } url='https://mainsite-restapi.ele.me/v2/pois?extras%5B%5D=count&geohash=wtsm0ss7yfj8&limit=20&type=nearby&'+parse.urlencode(key) cj = http.cookiejar.CookieJar() opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj)) opener.addheaders = [('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36'), ('Cookie', 'ubt_ssid=but8xnmtkpfrbvypd9z3hxaa5i8ugmj0_2017-04-29; _utrace=edd9bb6de13caed667d2cf273d73fc0a_2017-04-29')] urllib.request.install_opener(opener) html_bytes = urllib.request.urlopen(url).read() html_string = html_bytes.decode('utf-8') soup = BeautifulSoup(html_string, 'html.parser') try: info = eval(soup.prettify()) if len(info) and info is not None: return info[0] else: return 'error' except: return 'error' sql = "SELECT id,name FROM `village` where geohash is null" cur.execute(sql) data = cur.fetchall() for d in data: print(d[0]) geohash='' latitude='' longitude='' gh=getgeohash(d[1]) if gh=='error': geohash='error' latitude='' longitude='' else: geohash = gh['geohash'] latitude = gh['latitude'] longitude = gh['longitude'] print(geohash,latitude,longitude) # gh['geohash'] is None sql = "UPDATE `village` SET geohash=%s,latitude=%s,longitude=%s where id=%s" cur.execute(sql, (geohash,latitude,longitude,d[0])) cur.close()#关闭游标 conn.close()#释放数据库资源
__author__='LeoKim' from bs4 import BeautifulSoup import pymysql import urllib.request, urllib.parse, http.cookiejar from urllib import parse import pymysql import json import re conn=pymysql.connect(host='localhost',user='root',passwd='superhero',db='python_test',port=3306,charset='utf8') cur=conn.cursor()#获取一个游标 def getstore(village_id,geohash,latitude,longitude,limit): key={ 'geohash':geohash, 'latitude':latitude, 'longitude':longitude, 'limit':limit } url='https://mainsite-restapi.ele.me/shopping/restaurants?extras%5B%5D=activities&offset=0&terminal=web'+parse.urlencode(key) cj = http.cookiejar.CookieJar() opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj)) opener.addheaders = [('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36'), ('Cookie', 'ubt_ssid=but8xnmtkpfrbvypd9z3hxaa5i8ugmj0_2017-04-29; _utrace=edd9bb6de13caed667d2cf273d73fc0a_2017-04-29')] urllib.request.install_opener(opener) html_bytes = urllib.request.urlopen(url).read() html_string = html_bytes.decode('utf-8') soup = BeautifulSoup(html_string, 'html.parser') info = soup.prettify() jsonData = json.loads(info) for data in jsonData: print(data['id']) print(village_id) print(data['name']) print(data['recent_order_num']) print(data['address']) print(data['order_lead_time']) print(data['float_delivery_fee']) average_cost=0 if 'average_cost' in data: cost = re.findall(r'\d+', data['average_cost']) average_cost=cost[0] print(average_cost) print(data['rating']) print('---------------------------------------------') shop_id = data['id'] name = data['name'] address = data['address'] recent_order_num = data['recent_order_num'] order_lead_time = data['order_lead_time'] float_delivery_fee = data['float_delivery_fee'] rating = data['rating'] sql = "INSERT INTO `store` (`shop_id`,`village_id`,`name`,`address`,`recent_order_num`,`order_lead_time`,`float_delivery_fee`, `average_cost`, `rating`) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s)" cur.execute(sql, (shop_id,village_id,name, address, recent_order_num, order_lead_time, float_delivery_fee, average_cost, rating)) # getstore('wtst84g4g0u','31.91988','118.83238',30) sql = "SELECT id,name,geohash,latitude,longitude FROM `village` where id >482 and geohash is not null" cur.execute(sql) data = cur.fetchall() for d in data: village_id=d[0] geohash = d[2] latitude = d[3] longitude = d[4] getstore(village_id,geohash,latitude,longitude,30) cur.close()#关闭游标 conn.close()#释放数据库资源