話不多說~直接上**：
import requests
from bs4 import beautifulsoup as bs
import pandas as pd
def getonepage(url, lists):
response = requests.get(url)
print(type(response.text))
soup = bs(response.text, 'html.parser')
houselist = soup.find_all('li', class_='item')
print(houselist)
for house in houselist:
list =
if house.find('div', class_='info').find('span', class_='tag') == none:
elif house.find('div', class_='info').find('span', class_='tag').text == '':
else:
if house.find('div', class_='info').find('span', class_='area') == none:
elif house.find('div', class_='info').find('span', class_='area').text == '':
else:
return lists
def getallinfo():
list_all =
list_one =
for i in range(1, 13):
url_new = "" + str(i) + "/"
print(url_new)
list_all = list_all + getonepage(url_new, list_one)
h = pd.dataframe(columns=name, data=list_all)
h.to_csv('f:/houseinfo.csv', encoding='gb18030')
print(list_all)
def run():
getallinfo()
if __name__ == '__main__':
run()
後期將逐步更新技術.......
某航空積分商城爬蟲
import urllib.request import urllib.parse import urllib.error import json import jsonpath import pandas as pd import time url 可從fiddler中檢視 headers nam...
python 某美電商平台爬蟲
def run q,searchtype,page headermap guomeiheader.guomei url q,searchtype,page guomeijson mayi3.daili url,headermap.get headers utf 8 headermap.get may...
js 取值 賦值 獲取某標籤某屬性的值
1.取值 方法一 自定義屬性必須用getattribute 方法 var iframesrcattr document.getelementbyid importjsp getattribute src 獲取得到的值是 test.html 方法二 var iframesrcattr document...