分享一个自己写的百度域名工具,支持域名批量添加,批量抓取以及sitemap
上周完成的,现在分享出来。涉及百度旋转验证码。工具只需要你的ck(cookie)
都只分享部分代码:
一:(批量抓取)
def verify_2(tk,ds,crawl_url,session):
try:
###=====================过验证抓取====================
url = "https://ziyuan.baidu.com/crawltools/add"
params = {
"site": crawl_url
}
sid=get_crawltools_id(crawl_url)
data = {
"type": "pc" if zhuaqu_type==1 else "mobile",
"url": crawl_url,
"sid": sid[1],
"tk": tk,
"ds": ds,
"zz_auto_vcode": ""
}
response = session.post(url, headers=headers_2, params=params, data=data,timeout=30)
if str(response.text)=='{"status":101}':
print("链接为--{}--抓取失败".format(crawl_url))
else:
print("链接为--{}--抓取成功".format(crawl_url))
except:
print("抓取失败")
二:(批量添加)
def verify_2(tk,ds,insert_url,session):
##备注:此处为更新cookie中ab_sr 与SITEMAPZHITONG 字段值 目前测试无需检测 可跳过
url = "https://miao.baidu.com/abdr"
params = {
"_o": "https://ziyuan.baidu.com"
}
data = {
"data": "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",
"key_id": "1a10799d44f64fb0",
"enc": 2
}
data = json.dumps(data)
time.sleep(1.2)
response = session.post(url, headers=headers, cookies=cookies_data, params=params, data=data,timeout=30)
print(str(response.json()))
print(response.cookies.get('ab_sr'))
cookies_data["ab_sr"] = response.cookies.get('ab_sr')
cookies_data["SITEMAPZHITONG"] = str(response.json())
headers_2 = {
"Connection": "keep-alive",
"Pragma": "no-cache",
"Cache-Control": "no-cache",
"sec-ch-ua": "\" Not A;Brand\";v=\"99\", \"Chromium\";v=\"96\", \"Google Chrome\";v=\"96\"",
"sec-ch-ua-mobile": "?0",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36",
"content-type": "application/x-www-form-urlencoded; charset=UTF-8",
"accept": "application/json, text/javascript, */*; q=0.01",
"x-requested-with": "XMLHttpRequest",
"x-request-by": "baidu.ajax",
"sec-ch-ua-platform": "\"Windows\"",
"Origin": "https://ziyuan.baidu.com",
"Host": "ziyuan.baidu.com",
"Sec-Fetch-Site": "same-origin",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Dest": "empty",
"Referer": "https://ziyuan.baidu.com/site/siteadd",
"Accept-Language": "zh-CN,zh;q=0.9"
}
###过验证
"""
备注 :域名不带www的 链接改为 "https://ziyuan.baidu.com/site/add?confirm=1"
域名带www的 链接改为 "https://ziyuan.baidu.com/site/add"
"""
url = "https://ziyuan.baidu.com/site/add"
data = {
"url": insert_url,
"tk": tk,
"ds": ds
}
time.sleep(1)
response = session.post(url, headers=headers_2, cookies=cookies_data, data=data)
print(response.text)
id=response.json()['id']
###保存类型
url = "https://ziyuan.baidu.com/site/saveTypeStr"
data = {
"site": insert_url,
"type_str[]": "其它"
}
headers_2["Referer"]='https://ziyuan.baidu.com/site/sitespherepage?id={}&sites={}'.format(id,insert_url)
response = session.post(url, headers=headers_2, cookies=cookies_data,data=data)
print(response.text)
###最后的文件校验
"""
最后验证解析这一步很慢
就是这dns解析这一步
"""
url = "https://ziyuan.baidu.com/site/verify"
data = {
"id": id,
"type": "dns"
}
time.sleep(1)
headers_2["Referer"]='https://ziyuan.baidu.com/site/siteverify?id={}'.format(id)
response = session.post(url, headers=headers_2, cookies=cookies_data, data=data)
print(response.text)
三:(sitemap)
def verify_2(tk,ds,dns_url,sitemap_url,session):
url = "https://ziyuan.baidu.com/linksubmit/save"
params = {
"site": dns_url
}
data = {
"ds": ds,
"tk": tk,
"urls[]": sitemap_url
}
response = session.post(url, headers=headers, cookies=cookies_data, params=params, data=data)
print(response.text)
print(response)