- 600多行PY代码
- 涉及吾爱、知乎、bilibili、acfun、虎扑、什么值得买、微博、贴吧、少数派、36氪
- 本版本相对于高版本只是接口不再更新，代码复用率低点，乱点，bug还是会同高版本同时修复
"""
@author: webra
@time: 2023/3/27 13:31
@description:
@update: 2023/04/03 14:29:35
"""
import glob
import re
import time
import requests
from bs4 import BeautifulSoup
import datetime
import json
from lxml import etree
import random
import os
from flask import Flask
now = datetime.datetime.now()
timestamp = int(time.time())
app = Flask(__name__)
def read_file(file_path):
with open(file_path, 'r') as f:
content = f.read()
return content
def del_file(file_path):
if os.path.exists(file_path):
os.remove(file_path)
def write_file(file_path, content):
with open(file_path, 'w', encoding='utf-8') as f:
f.write(content)
@app.route("/")
def index():
data_dict = {"get_wuai_data": "吾爱热榜",
"get_zhihu_data": "知乎热榜",
"get_bilibili_data": "bilibili全站日榜",
"get_bilibili_hot": "bilibili热搜榜",
"get_acfun_data": "acfun热榜",
"get_hupu_data": "虎扑步行街热榜",
"get_smzdm_data": "什么值得买热榜",
"get_weibo_data": "微博热榜",
"get_tieba_data": "百度贴吧热榜",
"get_weixin_data": "微信热榜",
"get_ssp_data": "少数派热榜",
"get_36k_data": "36Kr热榜"}
json_data = {}
json_data["secure"] = True
json_data["title"] = "热榜接口"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
json_data["data"] = data_dict
return json.dumps(json_data, ensure_ascii=False)
@app.route("/test")
def test():
return "test"
user_agents = [
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Mobile Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246",
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246",
"Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; AS; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; AS; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; AS; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; Trident/7.0; AS; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0) Gecko/20100101 Firefox/54.0",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"
]
def random_user_agent():
return random.choice(user_agents)
def get_html(url, headers, cl=None):
response = requests.get(url, headers=headers, stream=True)
if cl is not None:
return response
html = BeautifulSoup(response.text, 'html.parser')
return html
def get_data(filename, filename_re):
file_names = glob.glob('./data/' + filename)
file_names_len = len(file_names)
if file_names_len == 1:
# 文件名
file_name = file_names[0]
old_timestamp = int(re.findall(filename_re, file_name)[0])
old_timestamp_datetime_obj = datetime.datetime.fromtimestamp(int(old_timestamp))
time_diff = datetime.datetime.now() - old_timestamp_datetime_obj
if time_diff > datetime.timedelta(hours=1):
del_file(file_name)
return None
else:
return read_file(file_name)
else:
if file_names_len > 1:
[del_file(file_name) for file_name in file_names]
return None
# 吾爱热榜
@app.route("/get_wuai_data")
def get_wuai_data():
filename = "wuai_data_*.data"
filename_re = "wuai_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "吾爱热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
"Accept-Encoding": "gzip, deflate, br",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
"User-Agent": random_user_agent()
}
html = get_html("https://www.52pojie.cn/forum.php?mod=guide&view=hot", headers)
articles = html.find_all('a', {'class': {"xst"}})
articles_hot = html.find_all('span', {'class': {"xi1"}})
num = 1
for article, hot in zip(articles, articles_hot):
data_dict = {}
data_dict["index"] = num
data_dict["title"] = article.string.strip()
data_dict["url"] = "https://www.52pojie.cn/" + article.get('href')
data_dict["hot"] = hot.string.strip()[:-3]
num += 1
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "wuai_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# 知乎热榜
@app.route("/get_zhihu_data")
def get_zhihu_data():
filename = "zhihu_data_*.data"
filename_re = "zhihu_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "知乎热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
'cookie': '_zap=3195f691-793a-404b-a1c2-a152ead6b0ef; d_c0=AYBTpKH7IxaPTlkD0uawrZWC1OzdedJsmVg=|1673151895; ISSW=1; YD00517437729195:WM_TID=dCD5z+kvXkZBERAERReVJ4HqjJV+UbEX; _xsrf=ZRKz2ahWNVIiiMuVsgwncHmiJEnJfxNP; __snaker__id=0oLAfHUBBwwPa2yi; YD00517437729195:WM_NI=aUaJNpP+BSZZKrXd9A4FtimocRtXflmIudVaB2GQ3pbhE4PJ/ZZQbOxBl7emji362eQ1fwxZYVDH4VyUpXdoZgqArTuIoIC+WCUJeEIZyTNSJhClos1zt2x+AhoVOlM+SFQ=; YD00517437729195:WM_NIKE=9ca17ae2e6ffcda170e2e6eea2b36bf5f1f783e9468a8a8eb6c15e869b8eb1c8458cafffd8e66da3b781ccd82af0fea7c3b92aa38bafabcd7c94f58eb4d95289ae9885bc4bf89abc8af065a18ebcb9e568af97bb85d56b82ee89b2b27ca2b88bd5d342ed8696b2e145bc9ea4d8e867aab7fdd7b16f93efaa98fb529b8a8ca9b75ebb8bc0b9e7659ab9bfa2f160b797a1aac221959d9babe84f8b86b7b5cd598ab88d8dee79f3a6bcd3fb2183b8a1b7ce688ff59da7d437e2a3; q_c1=0b5f766a729d4411b01730ae52526275|1677133529000|1677133529000; tst=h; z_c0=2|1:0|10:1679897427|4:z_c0|80:MS4xMjVueENnQUFBQUFtQUFBQVlBSlZUVk9CRG1VaWJoVGFZQ0JYaTczbzNLcy1qRXlucUc4SGlRPT0=|2071b379b81c9c1ee8a391002cd616468bc31ac1c1883f75bfaf93f099c5bce3; Hm_lvt_98beee57fd2ef70ccdd5ca52b9740c49=1679672991,1679721877,1679839421,1679897389; SESSIONID=XB0nPsBsUVHWlgxviypJUHFVjvA26oSiK1qkBbd9VO7; JOID=W1gQBEJCI1qbP0u7NExKANeQvpEuE2Ro-28x_EUXfBfOXSzKRx0Xd_E2R7w4R0VDXFi445KUxEew11n4txI14hY=; osd=U1ASB09KK1iYMkOzNk9HCN-SvZwmG2Zr9mc5_kYadB_MXiHCTx8Uevk-Rb81T01BX1Ww65CXyU-41Vr1vxo34Rs=; Hm_lpvt_98beee57fd2ef70ccdd5ca52b9740c49=1679901672; KLBRSID=81978cf28cf03c58e07f705c156aa833|1679902388|1679897426',
'referer': 'https://www.zhihu.com/',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent': random_user_agent()
}
html = get_html("https://www.zhihu.com/hot", headers, 1)
etree_html = etree.HTML(html.content.decode('utf-8'))
articles_title = etree_html.xpath('//*[@id="TopstoryContent"]/div/div/div[1]/section/div[2]/a/@title')
articles_url = etree_html.xpath('//*[@id="TopstoryContent"]/div/div/div[1]/section/div[2]/a/@href')
articles_hot = etree_html.xpath('//*[@id="TopstoryContent"]/div/div/div[1]/section/div[2]/div/text()')
num = 1
for title, url, hot in zip(articles_title, articles_url, articles_hot):
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = title
data_dict["url"] = url
data_dict["hot"] = hot[:-2]
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "zhihu_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# bilibili全站日榜，无got节点
@app.route("/get_bilibili_data")
def get_bilibili_data():
filename = "bilibili_data_*.data"
filename_re = "bilibili_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "哔哩哔哩全站热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
"User-Agent": random_user_agent()
}
html = get_html("https://api.bilibili.com/x/web-interface/ranking/v2?rid=0&type=all", headers, 1)
html_dict = json.loads(html.text)
num = 1
for key in html_dict["data"]["list"]:
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = key["title"]
data_dict["url"] = key["short_link"]
data_dict["hot"] = ""
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "bilibili_data_" + str(timestamp) + ".data"
print(filename)
write_file("./data/" + filename, data)
return data
else:
return file_content
# bilibili热搜榜
@app.route("/get_bilibili_hot")
def get_bilibili_hot():
filename = "bilibili_hot_*.data"
filename_re = "bilibili_hot_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "bilibili热搜榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
res = requests.get("https://app.bilibili.com/x/v2/search/trending/ranking")
html_dict = json.loads(res.text)
for key in html_dict["data"]["list"]:
data_dict = {}
data_dict["index"] = key["position"]
data_dict["title"] = key["show_name"]
url = "https://search.bilibili.com/all?keyword=" + key[
"keyword"] + "&from_source=webtop_search&spm_id_from=333.934"
data_dict["url"] = url
data_dict["hot"] = ""
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "bilibili_hot_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# acfun热榜
@app.route("/get_acfun_data")
def get_acfun_data():
filename = "acfun_data_*.data"
filename_re = "acfun_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "acfun热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
'referer': 'https://www.acfun.cn/',
'user-agent': random_user_agent()
}
res = get_html("https://www.acfun.cn/rest/pc-direct/rank/channel?channelId=&subChannelId=&rankLimit=30&rankPeriod=DAY", headers, 1)
html_dict = json.loads(res.text)
num = 1
for key in html_dict["rankList"]:
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = key["title"]
data_dict["url"] = key["shareUrl"]
data_dict["hot"] = key["viewCountShow"]
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "acfun_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# 虎扑步行街热榜
@app.route("/get_hupu_data")
def get_hupu_data():
filename = "hupu_data_*.data"
filename_re = "hupu_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "虎扑步行街热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
'referer': 'https://hupu.com/',
'user-agent': random_user_agent()
}
res = requests.get("https://bbs.hupu.com/all-gambia", headers=headers)
etree_html = etree.HTML(res.text)
articles_title = etree_html.xpath('//*[@id="container"]/div/div[2]/div/div[2]/div/div[2]/div/div/div/div[1]/a/span/text()')
articles_url = etree_html.xpath('//*[@id="container"]/div/div[2]/div/div[2]/div/div[2]/div/div/div/div[1]/a/@href')
articles_top = etree_html.xpath('//*[@id="container"]/div/div[2]/div/div[2]/div/div[2]/div/div/div/div[1]/span[1]/text()')
num = 1
for title, url, top in zip(articles_title, articles_url, articles_top):
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = title
data_dict["url"] = "https://bbs.hupu.com/" + url
data_dict["top"] = top
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "hupu_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# 什么值得买热榜（日榜）
@app.route("/get_smzdm_data")
def get_smzdm_data():
filename = "smzdm_data_*.data"
filename_re = "smzdm_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "什么值得买热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
'referer': 'https://smzdm.com/',
'user-agent': random_user_agent()
}
res = requests.get("https://post.smzdm.com/hot_1/", headers=headers)
etree_html = etree.HTML(res.text)
articles_title = etree_html.xpath('//*[@id="feed-main-list"]/li/div/div[2]/h5/a/text()')
articles_url = etree_html.xpath('//*[@id="feed-main-list"]/li/div/div[2]/h5/a/@href')
articles_top = etree_html.xpath('//*[@id="feed-main-list"]/li/div/div[2]/div[2]/div[2]/a[1]/span[2]/text()')
num = 1
for title, url, top in zip(articles_title, articles_url, articles_top):
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = title
data_dict["url"] = url
data_dict["top"] = top
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "smzdm_data_" + str(timestamp) + ".data"
print(data)
write_file("./data/" + filename, data)
return data
else:
return file_content
# 微博热榜
@app.route("/get_weibo_data")
def get_weibo_data():
filename = "weibo_data_*.data"
filename_re = "weibo_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "微博热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
'referer': 'https://smzdm.com/',
'user-agent': random_user_agent()
}
res = requests.get("https://weibo.com/ajax/statuses/hot_band", headers=headers)
html_dict = json.loads(res.text)
for key in html_dict["data"]["band_list"]:
try:
data_dict = {}
data_dict["index"] = key["realpos"]
data_dict["title"] = key["word"]
data_dict["url"] = "https://s.weibo.com/weibo?q=%23" + key["word"] + "%23"
data_dict["hot"] = key["num"]
except KeyError:
continue
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "weibo_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# 百度贴吧热议榜
@app.route("/get_tieba_data")
def get_tieba_data():
filename = "tieba_data_*.data"
filename_re = "tieba_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "百度贴吧热议榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
import requests
headers = {
'referer': 'https://tieba.baidu.com/',
'user-agent': random_user_agent()
}
res = requests.get("https://tieba.baidu.com/hottopic/browse/topicList?res_type=1", headers=headers)
etree_html = etree.HTML(res.text)
articles_title = etree_html.xpath('/html/body/div[2]/div/div[2]/div/div[2]/div[1]/ul/li/div/div/a/text()')
articles_url = etree_html.xpath('/html/body/div[2]/div/div[2]/div/div[2]/div[1]/ul/li/div/div/a/@href')
articles_top = etree_html.xpath('/html/body/div[2]/div/div[2]/div/div[2]/div[1]/ul/li/div/div/span[2]/text()')
num = 1
for title, url, top in zip(articles_title, articles_url, articles_top):
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = title
data_dict["url"] = url
data_dict["top"] = top.replace("实时讨论", "")
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "tieba_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# 微信热榜
# @app.route("/get_weixin_data")
# def get_weixin_data():
# json_data = {}
# data_list = []
# json_data["secure"] = True
# json_data["title"] = "微信热榜"
# json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
# import requests
# headers = {
# 'referer': 'https://tophub.today/',
# 'user-agent': random_user_agent()
# }
# res = requests.get("https://tophub.today/n/WnBe01o371", headers=headers)
# etree_html = etree.HTML(res.text)
# articles_title = etree_html.xpath('//*[@id="page"]/div[2]/div[2]/div[1]/div[2]/div/div[1]/table/tbody/tr/td[2]/a/text()')
# articles_url = etree_html.xpath('//*[@id="page"]/div[2]/div[2]/div[1]/div[2]/div/div[1]/table/tbody/tr/td[2]/a/@href')
# articles_top = etree_html.xpath('//*[@id="page"]/div[2]/div[2]/div[1]/div[2]/div/div[1]/table/tbody/tr/td[3]/text()')
# num = 1
# for title, url, top in zip(articles_title, articles_url, articles_top):
# data_dict = {}
# data_dict["index"] = num
# num += 1
# data_dict["title"] = title
# data_dict["url"] = "https://tophub.today" + url
# data_dict["top"] = top
# data_list.append(data_dict)
# json_data["data"] = data_list
# return json.dumps(json_data, ensure_ascii=False)
# 少数派热榜
@app.route("/get_ssp_data")
def get_ssp_data():
filename = "ssp_data_*.data"
filename_re = "ssp_data_(.*?).data"
file_content = get_data(filename, filename_re)
if file_content is None:
json_data = {}
data_list = []
json_data["secure"] = True
json_data["title"] = "少数派热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
headers = {
'referer': 'https://sspai.com/',
'user-agent': random_user_agent()
}
res = requests.get(
"https://sspai.com/api/v1/article/tag/page/get?limit=100000&tag=%E7%83%AD%E9%97%A8%E6%96%87%E7%AB%A0",
headers=headers)
html_dict = json.loads(res.text)
num = 1
for key in html_dict["data"]:
try:
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = key["title"]
data_dict["url"] = "https://sspai.com/post/" + str(key["id"])
data_dict["top"] = key["like_count"]
except KeyError:
continue
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "ssp_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
# 36Kr热榜
@app.route("/get_36k_data")
def html_get_36k_data():
json_data = {}
json_data["secure"] = True
json_data["title"] = "36Kr热榜"
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
data = [
{"type": "renqi"},
{"type": "shoucang"},
{"type": "zonghe"}
]
json_data["data"] = data
return json.dumps(json_data, ensure_ascii=False)
@app.route("/get_36k_data/<type>")
def get_36k_data_type(type):
if type == "renqi":
return get_36k_data("renqi")
elif type == "shoucang":
return get_36k_data("shoucang")
elif type == "zonghe":
return get_36k_data("zonghe")
else:
json_data = {}
json_data["secure"] = False
json_data["title"] = "Error"
return json.dumps(json_data, ensure_ascii=False)
# type = renqi| zonghe| shoucang
def get_36k_data(type):
json_data = {}
data_list = []
json_data["update_time"] = now.strftime("%Y-%m-%d %H:%M:%S")
filename = "36kr_" + type + "_data_*.data"
filename_re = "36kr_" + type + "_data_(.*?).data"
if type == "renqi":
title = "36Kr人气榜"
elif type == "zonghe":
title = "36Kr综合榜"
elif type == "shoucang":
title = "36Kr收藏榜"
else:
json_data["secure"] = False
json_data["title"] = "Error"
return json.dumps(json_data, ensure_ascii=False)
file_content = get_data(filename, filename_re)
if file_content is None:
json_data["secure"] = True
json_data["title"] = title
headers = {
'referer': 'https://www.36kr.com/',
'user-agent': random_user_agent()
}
url = "https://www.36kr.com/hot-list/" + type + "/" + now.strftime("%Y-%m-%d") + "/1"
res = requests.get(url, headers=headers)
etree_html = etree.HTML(res.text)
articles_title = etree_html.xpath('//*[@id="app"]/div/div[2]/div[3]/div/div/div[2]/div[1]/div/div/div/div/div[2]/div[2]/a/text()')
articles_url = etree_html.xpath('//*[@id="app"]/div/div[2]/div[3]/div/div/div[2]/div[1]/div/div/div/div/div[2]/div[2]/a/@href')
articles_top = etree_html.xpath('//*[@id="app"]/div/div[2]/div[3]/div/div/div[2]/div[1]/div/div/div/div/div[2]/div[2]/div/span/span/text()')
num = 1
for title, url, top in zip(articles_title, articles_url, articles_top):
data_dict = {}
data_dict["index"] = num
num += 1
data_dict["title"] = title
data_dict["url"] = "https://www.36kr.com" + url
data_dict["top"] = top.replace("热度", "")
data_list.append(data_dict)
json_data["data"] = data_list
data = json.dumps(json_data, ensure_ascii=False)
filename = "36kr_" + type + "_data_" + str(timestamp) + ".data"
write_file("./data/" + filename, data)
return data
else:
return file_content
if __name__ == "__main__":
app.run()
没有一为导航怎么测试调用啊
一为导航的后台设置中有主题自带的自定义热源，可以自己配置接口进行热榜或者其他数据展示。自定义的脚本搭建方法，可以见本文章，详细的后台操作可以加qq群或者微信私聊?
加你了 同意下
图片寄了啊 图片(i.imgur.com/qg3rmss.png) 图片(i.imgur.com/fjiqnxg.png)
这也不知道下一步怎么做啊
目前修复了，有看到吗
感谢站长，今天才看到（12.10），进入讯代理页面。发现正好提示停止运营了。。
没有啊，我用了好久了 这个代{1}理，怎么会停止运营呢？或者加入水友群(侧边栏最下方)、网页最底端有我的微信二维码，可以唠唠嗑
好的，你进官网看一下，那个官网上面写的
淦= =我刚看见 我的眼啊 瞎了 我去找找其他代理，不然52论坛搞不了
大神可以集合到rsshub上面，而且它已经自带来知乎、微博等榜单
一直对rss不太了解，所以也是第一次听rsshub这个东西
我大概看了下，虽然处理方法简单了，但是不能直接用于热榜榜单，还是需要二次加工才可以用，我这个基本框架已经写出来了，再增加新的榜单也容易
哈哈哈，感谢大神回复，我也是个小白，那就用大神的
学习一下，谢谢分享
试试看看被
为什么都是 7
好像是后台没有获取到，或者是你配置的有问题，具体可以加群或者私聊我