gpt4 book ai didi

php - 是否有可能使用 PHP 获取 Google 网站管理员工具 (GET) 数据?

转载 作者:可可西里 更新时间:2023-10-31 22:56:09 27 4
gpt4 key购买 nike

我正在尝试从 Google 网站站长工具 (GWT) 获取一些数据,我已经搜索了一些 API 文档和工具,但它们仅从 GWT 返回了一些数据。

我的需求:

需要从GWT获取以下数据,

(1)。 TOP_PAGES

(2)。 TOP_QUERIES

(3)。 CRAWL_ERRORS

(4)。内容错误

(5)。 CONTENT_KEYWORDS

(6)。内部链接

(7)。外部链接

(8)。社会事件

获取这些数据后,我需要为每个数据生成 Excel 文件。

已实现:

我从上面得到的数据很少并生成到 Excel 文件中。例如,

(1)。 TOP_PAGES

(2)。 TOP_QUERIES

(3)。内部链接

(4)。外部链接

(5)。 CONTENT_KEYWORDS

未实现:

我仍然没有得到像这样的主要部分/数据,

(1)。 CRAWL_ERRORS

(2)。内容错误

(3)。社会事件

供您引用的代码示例:

我在 PHP 中为这个 GWT API 使用了两个文件,

文件#1: ( gwdata.php )

 <?php
/**
* PHP class for downloading CSV files from Google Webmaster Tools.
*
* This class does NOT require the Zend gdata package be installed
* in order to run.
*
* Copyright 2012 eyecatchUp UG. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
* @author: Stephan Schmitz <eyecatchup@gmail.com>
* @link: https://code.google.com/p/php-webmaster-tools-downloads/
*/

class GWTdata
{
const HOST = "https://www.google.com";
const SERVICEURI = "/webmasters/tools/";

public $_language, $_tables, $_daterange, $_downloaded, $_skipped;
private $_auth, $_logged_in;

public function __construct()
{
$this->_auth = false;
$this->_logged_in = false;
$this->_language = "en";
$this->_daterange = array("","");
$this->_tables = array("TOP_PAGES", "TOP_QUERIES",
"CRAWL_ERRORS", "CONTENT_ERRORS", "CONTENT_KEYWORDS",
"INTERNAL_LINKS", "EXTERNAL_LINKS", "SOCIAL_ACTIVITY"
);
$this->_errTablesSort = array(0 => "http",
1 => "not-found", 2 => "restricted-by-robotsTxt",
3 => "unreachable", 4 => "timeout", 5 => "not-followed",
"kAppErrorSoft-404s" => "soft404", "sitemap" => "in-sitemaps"
);
$this->_errTablesType = array(0 => "web-crawl-errors",
1 => "mobile-wml-xhtml-errors", 2 => "mobile-chtml-errors",
3 => "mobile-operator-errors", 4 => "news-crawl-errors"
);
$this->_downloaded = array();
$this->_skipped = array();
}

/**
* Sets content language.
*
* @param $str String Valid ISO 639-1 language code, supported by Google.
*/
public function SetLanguage($str)
{
$this->_language = $str;
}

/**
* Sets features that should be downloaded.
*
* @param $arr Array Valid array values are:
* "TOP_PAGES", "TOP_QUERIES", "CRAWL_ERRORS", "CONTENT_ERRORS",
* "CONTENT_KEYWORDS", "INTERNAL_LINKS", "EXTERNAL_LINKS",
* "SOCIAL_ACTIVITY".
*/
public function SetTables($arr)
{
if(is_array($arr) && !empty($arr) && sizeof($arr) <= 2) {
$valid = array("TOP_PAGES","TOP_QUERIES","CRAWL_ERRORS","CONTENT_ERRORS",
"CONTENT_KEYWORDS","INTERNAL_LINKS","EXTERNAL_LINKS","SOCIAL_ACTIVITY");
$this->_tables = array();
for($i=0; $i < sizeof($arr); $i++) {
if(in_array($arr[$i], $valid)) {
array_push($this->_tables, $arr[$i]);
} else { throw new Exception("Invalid argument given."); }
}
} else { throw new Exception("Invalid argument given."); }
}

/**
* Sets daterange for download data.
*
* @param $arr Array Array containing two ISO 8601 formatted date strings.
*/
public function SetDaterange($arr)
{
if(is_array($arr) && !empty($arr) && sizeof($arr) == 2) {
if(self::IsISO8601($arr[0]) === true &&
self::IsISO8601($arr[1]) === true) {
$this->_daterange = array(str_replace("-", "", $arr[0]),
str_replace("-", "", $arr[1]));
return true;
} else { throw new Exception("Invalid argument given."); }
} else { throw new Exception("Invalid argument given."); }
}

/**
* Returns array of downloaded filenames.
*
* @return Array Array of filenames that have been written to disk.
*/
public function GetDownloadedFiles()
{
return $this->_downloaded;
}

/**
* Returns array of downloaded filenames.
*
* @return Array Array of filenames that have been written to disk.
*/
public function GetSkippedFiles()
{
return $this->_skipped;
}

/**
* Checks if client has logged into their Google account yet.
*
* @return Boolean Returns true if logged in, or false if not.
*/
private function IsLoggedIn()
{
return $this->_logged_in;
}

/**
* Attempts to log into the specified Google account.
*
* @param $email String User's Google email address.
* @param $pwd String Password for Google account.
* @return Boolean Returns true when Authentication was successful,
* else false.
*/
public function LogIn($email, $pwd)
{
$url = self::HOST . "/accounts/ClientLogin";
$postRequest = array(
'accountType' => 'HOSTED_OR_GOOGLE',
'Email' => $email,
'Passwd' => $pwd,
'service' => "sitemaps",
'source' => "Google-WMTdownloadscript-0.1-php"
);
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $postRequest);
$output = curl_exec($ch);
$info = curl_getinfo($ch);
curl_close($ch);
if($info['http_code'] == 200) {
preg_match('/Auth=(.*)/', $output, $match);
if(isset($match[1])) {
$this->_auth = $match[1];
$this->_logged_in = true;
return true;
} else { return false; }
} else { return false; }
}

/**
* Attempts authenticated GET Request.
*
* @param $url String URL for the GET request.
* @return Mixed Curl result as String,
* or false (Boolean) when Authentication fails.
*/
public function GetData($url)
{
if(self::IsLoggedIn() === true) {
$url = self::HOST . $url;
$head = array("Authorization: GoogleLogin auth=".$this->_auth,
"GData-Version: 2");
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_ENCODING, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, $head);
$result = curl_exec($ch);
$info = curl_getinfo($ch);
curl_close($ch);
return ($info['http_code']!=200) ? false : $result;
} else { return false; }
}

/**
* Gets all available sites from Google Webmaster Tools account.
*
* @return Mixed Array with all site URLs registered in GWT account,
* or false (Boolean) if request failed.
*/
public function GetSites()
{
if(self::IsLoggedIn() === true) {
$feed = self::GetData(self::SERVICEURI."feeds/sites/");
if($feed !== false) {
$sites = array();
$doc = new DOMDocument();
$doc->loadXML($feed);
foreach ($doc->getElementsByTagName('entry') as $node) {
array_push($sites,
$node->getElementsByTagName('title')->item(0)->nodeValue);
}
return $sites;
} else { return false; }
} else { return false; }
}

/**
* Gets the download links for an available site
* from the Google Webmaster Tools account.
*
* @param $url String Site URL registered in GWT.
* @return Mixed Array with keys TOP_PAGES and TOP_QUERIES,
* or false (Boolean) when Authentication fails.
*/
public function GetDownloadUrls($url)
{
if(self::IsLoggedIn() === true) {
$_url = sprintf(self::SERVICEURI."downloads-list?hl=%s&siteUrl=%s",
$this->_language,
urlencode($url));
$downloadList = self::GetData($_url);
return json_decode($downloadList, true);
} else { return false; }
}

/**
* Downloads the file based on the given URL.
*
* @param $site String Site URL available in GWT Account.
* @param $savepath String Optional path to save CSV to (no trailing slash!).
*/
public function DownloadCSV($site, $savepath=".")
{
if(self::IsLoggedIn() === true) {
$downloadUrls = self::GetDownloadUrls($site);
$filename = parse_url($site, PHP_URL_HOST) ."-". date("Ymd-His");
$tables = $this->_tables;
foreach($tables as $table) {
if($table=="CRAWL_ERRORS") {
self::DownloadCSV_CrawlErrors($site, $savepath);
}
elseif($table=="CONTENT_ERRORS") {
self::DownloadCSV_XTRA($site, $savepath,
"html-suggestions", "\)", "CONTENT_ERRORS", "content-problems-dl");
}
elseif($table=="CONTENT_KEYWORDS") {
self::DownloadCSV_XTRA($site, $savepath,
"keywords", "\)", "CONTENT_KEYWORDS", "content-words-dl");
}
elseif($table=="INTERNAL_LINKS") {
self::DownloadCSV_XTRA($site, $savepath,
"internal-links", "\)", "INTERNAL_LINKS", "internal-links-dl");
}
elseif($table=="EXTERNAL_LINKS") {
self::DownloadCSV_XTRA($site, $savepath,
"external-links-domain", "\)", "EXTERNAL_LINKS", "external-links-domain-dl");
}
elseif($table=="SOCIAL_ACTIVITY") {
self::DownloadCSV_XTRA($site, $savepath,
"social-activity", "x26", "SOCIAL_ACTIVITY", "social-activity-dl");
}
else {
$finalName = "$savepath/$table-$filename.csv";
$finalUrl = $downloadUrls[$table] ."&prop=ALL&db=%s&de=%s&more=true";
$finalUrl = sprintf($finalUrl, $this->_daterange[0], $this->_daterange[1]);
self::SaveData($finalUrl,$finalName);
}
}
} else { return false; }
}

/**
* Downloads "unofficial" downloads based on the given URL.
*
* @param $site String Site URL available in GWT Account.
* @param $savepath String Optional path to save CSV to (no trailing slash!).
*/
public function DownloadCSV_XTRA($site, $savepath=".", $tokenUri, $tokenDelimiter, $filenamePrefix, $dlUri)
{
if(self::IsLoggedIn() === true) {
$uri = self::SERVICEURI . $tokenUri . "?hl=%s&siteUrl=%s";
$_uri = sprintf($uri, $this->_language, $site);
$token = self::GetToken($_uri, $tokenDelimiter);
$filename = parse_url($site, PHP_URL_HOST) ."-". date("Ymd-His");
$finalName = "$savepath/$filenamePrefix-$filename.csv";
$url = self::SERVICEURI . $dlUri . "?hl=%s&siteUrl=%s&security_token=%s&prop=ALL&db=%s&de=%s&more=true";
$_url = sprintf($url, $this->_language, $site, $token, $this->_daterange[0], $this->_daterange[1]);
self::SaveData($_url,$finalName);
} else { return false; }
}

/**
* Downloads the Crawl Errors file based on the given URL.
*
* @param $site String Site URL available in GWT Account.
* @param $savepath String Optional: Path to save CSV to (no trailing slash!).
* @param $separated Boolean Optional: If true, the method saves separated CSV files
* for each error type. Default: Merge errors in one file.
*/
public function DownloadCSV_CrawlErrors($site, $savepath=".", $separated=false)
{
if(self::IsLoggedIn() === true) {
$type_param = "we";
$filename = parse_url($site, PHP_URL_HOST) ."-". date("Ymd-His");
if($separated) {
foreach($this->_errTablesSort as $sortid => $sortname) {
foreach($this->_errTablesType as $typeid => $typename) {
if($typeid == 1) {
$type_param = "mx";
} else if($typeid == 2) {
$type_param = "mc";
} else {
$type_param = "we";
}
$uri = self::SERVICEURI."crawl-errors?hl=en&siteUrl=$site&tid=$type_param";
$token = self::GetToken($uri,"x26");
$finalName = "$savepath/CRAWL_ERRORS-$typename-$sortname-$filename.csv";
$url = self::SERVICEURI."crawl-errors-dl?hl=%s&siteUrl=%s&security_token=%s&type=%s&sort=%s";
$_url = sprintf($url, $this->_language, $site, $token, $typeid, $sortid);
self::SaveData($_url,$finalName);
}
}
}
else {
$uri = self::SERVICEURI."crawl-errors?hl=en&siteUrl=$site&tid=$type_param";
$token = self::GetToken($uri,"x26");
$finalName = "$savepath/CRAWL_ERRORS-$filename.csv";
$url = self::SERVICEURI."crawl-errors-dl?hl=%s&siteUrl=%s&security_token=%s&type=0";
$_url = sprintf($url, $this->_language, $site, $token);
self::SaveData($_url,$finalName);
}
} else { return false; }
}

/**
* Saves data to a CSV file based on the given URL.
*
* @param $finalUrl String CSV Download URI.
* @param $finalName String Filepointer to save location.
*/
private function SaveData($finalUrl, $finalName)
{
$data = self::GetData($finalUrl);
if(strlen($data) > 1 && file_put_contents($finalName, utf8_decode($data))) {
array_push($this->_downloaded, realpath($finalName));
return true;
} else {
array_push($this->_skipped, $finalName);
return false;
}
}

/**
* Regular Expression to find the Security Token for a download file.
*
* @param $uri String A Webmaster Tools Desktop Service URI.
* @param $delimiter String Trailing delimiter for the regex.
* @return String Returns a security token.
*/
private function GetToken($uri, $delimiter)
{
$matches = array();
$tmp = self::GetData($uri);
//preg_match_all("#x26security_token(.*?)$delimiter#si", $tmp, $matches);
preg_match_all("#46security_token(.*?)$delimiter#si", $tmp, $matches);
//return substr($matches[1][0],4,-1);
return substr($matches[1][0],3,-1);
}

/**
* Validates ISO 8601 date format.
*
* @param $str String Valid ISO 8601 date string (eg. 2012-01-01).
* @return Boolean Returns true if string has valid format, else false.
*/
private function IsISO8601($str)
{
$stamp = strtotime($str);
return (is_numeric($stamp) && checkdate(date('m', $stamp),
date('d', $stamp), date('Y', $stamp))) ? true : false;
}
}
?>

文件#2: ( index.php )

<?php
include 'gwtdata.php';
include 'credentials.php';
try {
$website = "http://www.yourdomain.com/"; /* Add Your Website Url */
$gdata = new GWTdata();
if($gdata->LogIn($email, $password) === true)
{
$gdata->DownloadCSV($website,"Here Add Your Folder Path To Save CSV File With GWT Data");
echo "Datas Are Successfully Downloaded";
}
} catch (Exception $e) {
die($e->getMessage());
}
?>

任何人都可以帮助我实现所有这些数据并将其制作为 excel 文件以使用 PHP 生成。

最佳答案

[..] I have searched some of the API Documents and Implements, [..]
[..] I have used two files in PHP for this GWT API, [..]

我是您引用的代码(GWTdata PHP 类)的作者,首先要明确表示此代码既不由 Google 发布也不使用一个官方 API,而是一个自定义脚本,用于处理来自 Web 界面的数据。

[..] returning few of the datas only from the GWT. [..]

几周前,Google 网站站长工具网络界面发生了一些变化(同样,它曾经/现在用于处理数据请求)。因此,它破坏了 PHP 类 GWTdata 的某些功能 - 例如下载爬网错误。

[..] Can anyone help me in this, to achieve all those datas and make it as excel file to generate using PHP. [..]

不幸的是,对于大多数数据,我/我们对此无能为力(因为数据不再可访问)。

[..] Still I'm not getting the major parts / datas like,
1. Crawl errors [..]

无论如何,你可以使用this followup project获取抓取错误。

GwtCrawlErrors(以 CSV 格式从 Google 网站站长工具下载网站抓取错误):
https://github.com/eyecatchup/GWT_CrawlErrors-php

关于php - 是否有可能使用 PHP 获取 Google 网站管理员工具 (GET) 数据?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/15611372/

27 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com