Python_爬虫_requests小实战

 1 ##爬取任意地方肯德基的餐厅所有位置信息（数据以获取但还没分析。）
 2 import requests
 3 
 4 url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'
 5 user_input = input("enter a search:")
 6 headers = {
 7     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"
 8 }
 9 for i in range(1,20):
10     data = {
11         "cname":"",
12         "pid":"",
13         "keyword":user_input,
14         "pageIndex":i,
15         "pageSize": '10'
16     }
17     res = requests.post(url=url, data=data, headers=headers)
18     stats = res.headers
19     content = res.text
20     print(content+"\n")
21     try:
22         if not  stats["Vary"]:
23            pass
24     except:
25         break

 

爬取豆瓣电影中更多的电影详情数据（数据以获取但还没分析。）
import requests
headers = {
   "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"
 }
#https://movie.douban.com/j/chart/top_list?type=10&interval_id=100%3A90&action=&start=0&limit=1//悬疑
#https://movie.douban.com/j/chart/top_list?type=17&interval_id=100%3A90&action=&start=0&limit=20/科幻
#https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90&action=&start=0&limit=20//剧情
#https://movie.douban.com/j/chart/top_list?type=24&interval_id=100%3A90&action=&start=0&limit=20//喜剧
#https://movie.douban.com/j/chart/top_list?type=13&interval_id=100%3A90&action=&start=0&limit=20//爱情
#https://movie.douban.com/j/chart/top_list?type=25&interval_id=100%3A90&action=&start=0&limit=20//动画
url_secelt = {
    "动作":"5",
    "悬疑":"10",
    "科幻":"17",
    "剧情":"11",
    "喜剧":"24",
    "爱情":"13",
    "动画":"25"
}
user_movie = input("请输入电影类型 \n目前只支持搜索：动作 喜剧 科幻 剧情 爱情 动画 悬疑 \n")
url = 'https://movie.douban.com/j/chart/top_list?type={}&interval_id=100%3A90&action=None'.format(url_secelt[user_movie])
for i in range(0,800,20):
    param = {
        "start":i,
        "limit":"20"
    }
    res = requests.get(url=url,params=param,headers=headers)
    content = res.json()
    stats = res.headers
    if content == []:
        break
    print(content)
    try:
        if not stats["Vary"]:
            pass
    except:
        break

 

##http://125.35.6.84:81/xk/ 爬取一页每家企业的企业详情数据 （数据以获取但还没分析。）
import requests
headers = {
   "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"
 }
url = "http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList"

data = {
    "on": 'true',
    "page": "3",
    "pageSize": "15",
    "productName": "",
    "conditionType": "1",
    "applyname": "",
    "applysn": ""
}
res = requests.post(url=url,data=data,headers=headers)
content = res.json()
for i in content["list"]:
    url = "http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById"
    data = {
        "id": i["ID"]

    }
    res = requests.post(url=url, data=data, headers=headers)
    content = res.json()
    print(content)
#