Cloudmistery 6 months ago
parent
commit
6532986841

BIN
utils/__pycache__/anjuke_response.cpython-39.pyc


BIN
utils/__pycache__/setting.cpython-39.pyc


+ 2 - 2
utils/anjuke_response.py

@@ -7,7 +7,7 @@ import requests
 from anjuke.utils.setting import *
 
 # 请求返回
-response_origion = requests.get(url = url_start, headers=headers).content.decode('utf8')
-response_200 = requests.get(url = url_start, headers=headers)
+response_origion = requests.get(url = url_start, headers=headers,proxies=proxies, timeout=10).content.decode('utf8')
+response_200 = requests.get(url = url_start, headers=headers,proxies=proxies, timeout=10)
 
 print(response_origion,response_200)

+ 4 - 5
utils/get_message.py

@@ -11,7 +11,7 @@ import time,random
 def get_province():
     province_name_list = []
     province_url_list = []
-    response_province = requests.get(url = url_start, headers = headers).content.decode('utf8')
+    response_province = requests.get(url = url_start, headers = headers, proxies=proxies, timeout=10).content.decode('utf8')
     time.sleep(random.uniform(0.5, 1))
     soup = BeautifulSoup(response_province, 'html.parser')
     # print(soup)
@@ -23,7 +23,6 @@ def get_province():
         province_name_list.append(province_name)
         province_url_list.append('https://www.anjuke.com'+province_url)
     del province_name_list[0],province_url_list[0]
-    time.sleep(random.uniform(0.5, 1))
     return province_name_list,province_url_list
 
 # 市级
@@ -34,7 +33,7 @@ def get_city():
     for i in range(len(province_url_list)):
         province_url = province_url_list[i]
         province_name = province_name_list[i]
-        response_city = requests.get(url = province_url, headers = headers).content.decode('utf8')
+        response_city = requests.get(url = province_url, headers = headers, proxies=proxies, timeout=10).content.decode('utf8')
         time.sleep(random.uniform(3, 4))
         soup = BeautifulSoup(response_city, 'html.parser')
         filter_area_wrap = soup.find(class_="sel-content bank")
@@ -60,7 +59,7 @@ def get_area():
     for i in range(len(city_url_list)):
         city_url = city_url_list[i]
         city_name = city_name_list[i]
-        response_area = requests.get(url = city_url, headers = headers).content.decode('utf8')
+        response_area = requests.get(url = city_url, headers = headers ,proxies=proxies, timeout=10).content.decode('utf8')
         time.sleep(random.uniform(2, 3))
         soup = BeautifulSoup(response_area, 'html.parser')
         filter_area_wrap = soup.find(class_="sel-content bank")
@@ -86,7 +85,7 @@ def get_periphery():
     for i in range(len(area_url_list)):
         area_url = area_url_list[i]
         area_name = area_name_list[i]
-        response_periphery = requests.get(url = area_url, headers = headers).content.decode('utf8')
+        response_periphery = requests.get(url = area_url, headers = headers ,proxies=proxies, timeout=10).content.decode('utf8')
         time.sleep(random.uniform(3, 5))
         soup = BeautifulSoup(response_periphery, 'html.parser')
         filter_area_wrap = soup.find(class_="sel-content bank")

+ 26 - 12
utils/setting.py

@@ -4,11 +4,9 @@
 # @File    : setting.py
 import random
 
-
 # 模拟请求头
 agent_list = [
 	"Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
-	"Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)",
 	"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
 	"Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
 	"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
@@ -36,16 +34,32 @@ url_start = 'https://www.anjuke.com/fangjia/quanguo2024/'
 #     'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0'
 # }
 
-headers = {
-'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
-'accept-encoding':'gzip, deflate, br, zstd',
-'accept-language':'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
-'cache-control':'max-age=0',
-'connection':'keep-alive',
-'cookie':'aQQ_ajkguid=8A58B742-7F9E-4169-9684-065B9DF9AC96; sessid=2C9914D2-0EC1-4CF8-8B9F-BB2DD2432060; ajk-appVersion=; ctid=33; obtain_by=2; twe=2; id58=CkwAb2cHJ2CSvzjwJRw2Ag==; xxzlclientid=ac98d936-a0a8-41cf-b57a-1728522083413; xxzlxxid=pfmxpoucXXdKPZe3nePjn1oG3tEFYp6CwGDK9cSqkSE8FQ+YKsyHR+C1hZCtXLFDNP0S; fzq_h=bfec261cadc68ed6a35b0159901cf584_1728609619502_56d94ea5cdbf416fac02c5b4f2d27600_47896428890875912854068920960365571880; xxzlbbid=pfmbM3wxMDM0NnwxLjEwLjF8MTcyODYxMDg4MjI2MTg3OTkyMXwvak5hTThZUkZuRzE1TkkxbnJKaVBDZnZvTUR5WjB0QXA4dUtlZDZ2VWVrPXw0ZTM5ZmI1NzdkM2QyMGM1ZGJkM2I3MDEyNDQ5ODU3N18xNzI4NjEwODgxODU5Xzk1MjY2MTViNmRhMjQ3NmQ5ZGU5MDlkNWI4OGYyNzM4XzM3MDQ0ODAwNjB8ZTc0OWUyMTUyNTMzMzUzMzM4ZGZjZmE5ODY4NWE3OGNfMTcyODYxMDg4MTg0NV8yNTU=',
-'host':'www.anjuke.com',
-'if-none-match':"2db91-inlYvGp0xIvRpS6/mdxeLVOjQ9k",
-'user-agent':random.choice(agent_list),
+
+proxyHost = "proxy.abuyun.com"
+proxyPort = "9020"
+proxyUser = "H4ZX1CL3L0535Y5D"
+proxyPass = "6C1BEE51BA5C341C"
+proxyMeta = "http://%(user)s:%(pass)s@%(host)s:%(port)s" % {
+    "host": proxyHost,
+    "port": proxyPort,
+    "user": proxyUser,
+    "pass": proxyPass,
+}
+
+proxies = {
+    "http": proxyMeta,
+    "https": proxyMeta,
 }
 
 
+headers = {
+	'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+	'accept-encoding':'gzip, deflate, br, zstd',
+	'accept-language':'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+	'cache-control':'max-age=0',
+	'connection':'keep-alive',
+	'cookie':'aQQ_ajkguid=8A58B742-7F9E-4169-9684-065B9DF9AC96; sessid=2C9914D2-0EC1-4CF8-8B9F-BB2DD2432060; ajk-appVersion=; ctid=33; obtain_by=2; twe=2; id58=CkwAb2cHJ2CSvzjwJRw2Ag==; xxzlclientid=ac98d936-a0a8-41cf-b57a-1728522083413; xxzlxxid=pfmxpoucXXdKPZe3nePjn1oG3tEFYp6CwGDK9cSqkSE8FQ+YKsyHR+C1hZCtXLFDNP0S; fzq_h=bfec261cadc68ed6a35b0159901cf584_1728609619502_56d94ea5cdbf416fac02c5b4f2d27600_47896428890875912854068920960365571880; xxzlbbid=pfmbM3wxMDM0NnwxLjEwLjF8MTcyODYxMDg4MjI2MTg3OTkyMXwvak5hTThZUkZuRzE1TkkxbnJKaVBDZnZvTUR5WjB0QXA4dUtlZDZ2VWVrPXw0ZTM5ZmI1NzdkM2QyMGM1ZGJkM2I3MDEyNDQ5ODU3N18xNzI4NjEwODgxODU5Xzk1MjY2MTViNmRhMjQ3NmQ5ZGU5MDlkNWI4OGYyNzM4XzM3MDQ0ODAwNjB8ZTc0OWUyMTUyNTMzMzUzMzM4ZGZjZmE5ODY4NWE3OGNfMTcyODYxMDg4MTg0NV8yNTU=',
+	'host':'www.anjuke.com',
+	'if-none-match':"2db91-inlYvGp0xIvRpS6/mdxeLVOjQ9k",
+	'user-agent':random.choice(agent_list)
+}