import requests
import csv
import re
import random
import codecs
from bs4 import BeautifulSoup
import time
sleeptime = 1
list_name=[]
list_buff_price=[]
list_steam_price=[]
list_fa=[];
user_agent = [
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
"Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
"Openwave/ UCWEB7.0.2.37/28/999",
"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
]
#headers = {'User-Agent': random.choice(user_agent)}
def get_steam_page(url):
headers={
'Cookie':'
'user-agent':random.choice(user_agent),
'Accept-Language':'en-US,en;q=0.5',
'Connection': 'keep-alive'
}
res = requests.get(url)
soup = BeautifulSoup(res.text, "html.parser")
return soup
def get_buff_page(url):
headers={
'Cookie':'
'user-agent':random.choice(user_agent),
'Accept-Language':'en-US,en;q=0.5',
'Connection': 'keep-alive'
}
res = requests.get(url)
soup = BeautifulSoup(res.text, "html.parser")
return soup
def steam_page(soup):
grid = soup.find('div',attrs={"id": "BG_bottom"})
goods = grid.find('div',attrs={"id":"searchResultsRows"})
price_steam = goods.find("span",attrs={"calss","market_listing_price market_listing_price_with_fee"})
#print(price_steam)
print(price_steam.get_text().strip())
list_steam_price.append(price_steam.get_text().strip())
def parse_page(soup):
#return_list = []
#大容器
grid = soup.find('div',attrs={"class": "market-list"})
if grid:
#名稱
goods_name = grid.find('div',attrs={"class" : "detail-cont"})
goods_name1 = goods_name.find('h1').get_text().strip()
print(goods_name1)
list_name.append(goods_name1)
#steam鏈接
href = grid.find('div',attrs={"class": "detail-summ"})
href1 = href.find_all('a')[2]
#for i in href1:
url_steam = href1.get('href').strip()
print(url_steam);
#價格
price0 = grid.find('div',attrs={"class":"relative-goods"})
price1= price0.find('a')
#print(price1.get('data-price'))
st = str(price0.find('a',attrs={"class":"i_Btn i_Btn_trans_bule active"}))
#print(str(st))
st1 = st[st.find('data-price')+12:st.find('data-type')-2]
print(st1)
list_buff_price.append(st1)
soup = get_steam_page(url_steam)
steam_page(soup)
'''
for i in price0.find_all('a'):
print(i.get_text())
'''
# 42000,44100
#
for i in range(42000,42010):
print("當前進度"+str(i+1)+"\n")
url = 'https://buff.163.com/market/goods?goods_id='+str(i)
soup = get_buff_page(url)
parse_page(soup)
#list_fa.append(i);
#print (str(i+1)+"錯誤")
print ("*******************************************\n完成\n失敗頁為")
with open("buff.csv","a",encoding ="gb18030",newline="")as csvfile:
writer = csv.writer(csvfile)
#writer.writerow(["名字","價格","數量"])
for i in range(len(list_name)):
writer.writerow([list_name[i],list_buff_price[i],list_steam_price[i]])
print ("*******************************************\n寫入完成\n")

代碼結果如圖
uj5u.com熱心網友回復:
自己寫代碼轉換一下吧轉載請註明出處,本文鏈接:https://www.uj5u.com/qita/232731.html
