dw中怎样做网站二级页面,宁波市建设工程检测协会网站,安康地seo,做冷冻食品的网站大家好#xff0c;今天我要分享的是一个实用的Python脚本#xff0c;它可以帮助你批量获取CSDN博客上所有发布文章的相关数据#xff0c;并将这些数据保存到Excel文件中。此外#xff0c;脚本还会为每篇文章获取一个质量分#xff0c;并将这个分数也记录在Excel中。让我们…大家好今天我要分享的是一个实用的Python脚本它可以帮助你批量获取CSDN博客上所有发布文章的相关数据并将这些数据保存到Excel文件中。此外脚本还会为每篇文章获取一个质量分并将这个分数也记录在Excel中。让我们开始吧
脚本功能概述
这个脚本主要分为两个部分
获取文章信息并保存到Excel这部分会从CSDN API获取你的文章列表并将关键信息保存到Excel文件中。获取文章质量分并更新Excel这部分会为每篇文章请求一个质量分并将这个分数添加到对应的Excel文件中。
实现步骤
1. 导入必要的库
首先我们需要导入一些Python库来帮助我们完成这个任务
import json
import pandas as pd
from openpyxl import Workbook, load_workbook
from openpyxl.utils.dataframe import dataframe_to_rows
import math
import requests2. 定义获取文章信息并保存到Excel的类
我们定义了一个类 GetInformationToExcel 来处理文章信息的获取和Excel文件的保存
class GetInformationToExcel:def __init__(self, username, cookies, Referer, page, size, filename):self.username usernameself.cookies cookiesself.Referer Refererself.size sizeself.filename filenameself.page page# 发送HTTP GET请求到CSDN的API获取文章列表def get_articles(self):url https://blog.csdn.net/community/home-api/v1/get-business-listparams {page: {self.page},size: {self.size},businessType: blog,username: {self.username}}headers {User-Agent: Mozilla/5.0 (Windows NT 11.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3,Cookie: self.cookies,Referer: self.Referer}try:response requests.get(url, paramsparams, headersheaders)response.raise_for_status()data response.json()return data.get(data, {}).get(list, [])except requests.exceptions.HTTPError as e:print(fHTTP错误: {e.response.status_code} {e.response.reason})except requests.exceptions.RequestException as e:print(f请求异常: {e})except json.JSONDecodeError:print(解析JSON失败)return []# 将文章列表转换为Pandas DataFrame,选择并重命名必要的列。def export_to_excel(self):df pd.DataFrame(self.get_articles())df df[[title, url, postTime, viewCount, collectCount, diggCount, commentCount]]df.columns [文章标题, URL, 发布时间, 阅读量, 收藏量, 点赞量, 评论量]wb Workbook()sheet wb.activefor r in dataframe_to_rows(df, indexFalse, headerTrue):sheet.append(r)for column in sheet.columns:max_length 0column [cell for cell in column]for cell in column:try:if len(str(cell.value)) max_length:max_length len(cell.value)except:passadjusted_width (max_length 5)sheet.column_dimensions[column[0].column_letter].width adjusted_width# Save the workbookwb.save(self.filename)
在这个类中我们实现了以下方法
__init__初始化方法设置类的基本属性。get_articles发送HTTP GET请求到CSDN的API获取文章列表。export_to_excel将文章列表转换为Pandas DataFrame并保存到Excel文件。
3. 定义获取文章质量分的类
接下来我们定义了另一个类 GetArticleScores 来处理文章质量分的获取和Excel文件的更新
class GetArticleScores:def __init__(self, filepath):self.filepath filepath# 发送HTTP POST请求到一个API获取文章的质量分。staticmethoddef get_article_score(article_url):url https://bizapi.csdn.net/trends/api/v1/get-article-scoreheaders {Accept: application/json, text/plain, */*,X-Ca-Key: 203930474,X-Ca-Nonce: b35e1821-05c2-458d-adae-3b720bb15fdf,X-Ca-Signature: gjeSiKTRCh8aDv0UwThIVRITc/JtGJkgkZoLVeA6sWo,X-Ca-Signature-Headers: x-ca-key,x-ca-nonce,X-Ca-Signed-Content-Type: multipart/form-data,}data {url: article_url}try:response requests.post(url, headersheaders, datadata)response.raise_for_status() # This will raise an error for bad responsesreturn response.json().get(data, {}).get(score, Score not found)except requests.RequestException as e:print(fRequest failed: {e})return Error fetching scoredef get_scores_from_excel(self):读取Excel文件获取文章URL列表。对每个URL调用 get_article_score 方法获取分数列表。返回分数列表。df pd.read_excel(self.filepath)urls df[URL].tolist()scores [self.get_article_score(url) for url in urls]return scoresdef write_scores_to_excel(self):读取Excel文件到DataFrame。将获取的分数添加到DataFrame中。将更新后的DataFrame保存回Excel文件。df pd.read_excel(self.filepath)df[质量分] self.get_scores_from_excel()df.to_excel(self.filepath, indexFalse)在这个类中我们实现了以下方法
__init__初始化方法设置类的基本属性。get_article_score静态方法发送HTTP POST请求到一个API获取文章的质量分。get_scores_from_excel读取Excel文件获取文章URL列表并获取分数列表。write_scores_to_excel读取Excel文件到DataFrame将获取的分数添加到DataFrame中并保存回Excel文件。
4. 主程序
最后我们在主程序中设置了文章总数、cookies、Referer和CSDN用户ID并执行了以下步骤
计算需要请求的页数。循环处理每一页的文章创建Excel文件并获取质量分写入Excel。
if __name__ __main__:# 请填写:已发文章总数量,cookies,你的首页Referer你的idCSDNidtotal 145cookies uuid_tt_dd10 # Simplified for brevityReferer https://blog.csdn.net/q244645787CSDNid q244645787# 下面是计算和获取t_index math.ceil(total / 100) 1 # 向上取整半闭半开区间开区间1。for index in range(1, t_index): # 文章总数filename score str(index) .xlsxexporter_excel GetInformationToExcel(CSDNid, cookies, Referer, index, 100, filename) # Replace with your usernameexporter_excel.export_to_excel()article_score GetArticleScores(filename)article_score.write_scores_to_excel()print(获取完成)
执行完毕后你会得到包含所有文章数据和质量分的Excel文件。
所有代码
import json
import pandas as pd
from openpyxl import Workbook, load_workbook
from openpyxl.utils.dataframe import dataframe_to_rows
import math
import requests# 批量获取文章信息并保存到excel
class GetInformationToExcel:def __init__(self, username, cookies, Referer, page, size, filename):self.username usernameself.cookies cookiesself.Referer Refererself.size sizeself.filename filenameself.page page# 发送HTTP GET请求到CSDN的API获取文章列表def get_articles(self):url https://blog.csdn.net/community/home-api/v1/get-business-listparams {page: {self.page},size: {self.size},businessType: blog,username: {self.username}}headers {User-Agent: Mozilla/5.0 (Windows NT 11.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3,Cookie: self.cookies,Referer: self.Referer}try:response requests.get(url, paramsparams, headersheaders)response.raise_for_status()data response.json()return data.get(data, {}).get(list, [])except requests.exceptions.HTTPError as e:print(fHTTP错误: {e.response.status_code} {e.response.reason})except requests.exceptions.RequestException as e:print(f请求异常: {e})except json.JSONDecodeError:print(解析JSON失败)return []# 将文章列表转换为Pandas DataFrame,选择并重命名必要的列。def export_to_excel(self):df pd.DataFrame(self.get_articles())df df[[title, url, postTime, viewCount, collectCount, diggCount, commentCount]]df.columns [文章标题, URL, 发布时间, 阅读量, 收藏量, 点赞量, 评论量]wb Workbook()sheet wb.activefor r in dataframe_to_rows(df, indexFalse, headerTrue):sheet.append(r)for column in sheet.columns:max_length 0column [cell for cell in column]for cell in column:try:if len(str(cell.value)) max_length:max_length len(cell.value)except:passadjusted_width (max_length 5)sheet.column_dimensions[column[0].column_letter].width adjusted_width# Save the workbookwb.save(self.filename)# 获取每篇文章的质量分并将分数写入到Excel文件中
class GetArticleScores:def __init__(self, filepath):self.filepath filepath# 发送HTTP POST请求到一个API获取文章的质量分。staticmethoddef get_article_score(article_url):url https://bizapi.csdn.net/trends/api/v1/get-article-scoreheaders {Accept: application/json, text/plain, */*,X-Ca-Key: 203930474,X-Ca-Nonce: b35e1821-05c2-458d-adae-3b720bb15fdf,X-Ca-Signature: gjeSiKTRCh8aDv0UwThIVRITc/JtGJkgkZoLVeA6sWo,X-Ca-Signature-Headers: x-ca-key,x-ca-nonce,X-Ca-Signed-Content-Type: multipart/form-data,}data {url: article_url}try:response requests.post(url, headersheaders, datadata)response.raise_for_status() # This will raise an error for bad responsesreturn response.json().get(data, {}).get(score, Score not found)except requests.RequestException as e:print(fRequest failed: {e})return Error fetching scoredef get_scores_from_excel(self):读取Excel文件获取文章URL列表。对每个URL调用 get_article_score 方法获取分数列表。返回分数列表。df pd.read_excel(self.filepath)urls df[URL].tolist()scores [self.get_article_score(url) for url in urls]return scoresdef write_scores_to_excel(self):读取Excel文件到DataFrame。将获取的分数添加到DataFrame中。将更新后的DataFrame保存回Excel文件。df pd.read_excel(self.filepath)df[质量分] self.get_scores_from_excel()df.to_excel(self.filepath, indexFalse)if __name__ __main__:# 请填写:已发文章总数量,cookies,你的首页Referer你的idCSDNidtotal 145cookies uuid_tt_dd10 # Simplified for brevityReferer https://blog.csdn.net/q244645787CSDNid q244645787# 下面是计算和获取t_index math.ceil(total / 100) 1 # 向上取整半闭半开区间开区间1。for index in range(1, t_index): # 文章总数filename score str(index) .xlsxexporter_excel GetInformationToExcel(CSDNid, cookies, Referer, index, 100, filename) # Replace with your usernameexporter_excel.export_to_excel()article_score GetArticleScores(filename)article_score.write_scores_to_excel()print(获取完成)效果
