Python爬取51cto數(shù)據(jù)并存入MySQL方法詳解

【相關(guān)學(xué)習(xí)推薦：python教程】

讓客戶滿意是我們工作的目標，不斷超越客戶的期望值來自于我們對這個行業(yè)的熱愛。我們立志把好的技術(shù)通過有效、簡單的方式提供給客戶，將通過不懈努力成為客戶在信息化領(lǐng)域值得信任、有價值的長期合作伙伴，公司提供的服務(wù)項目有：國際域名空間、虛擬空間、營銷軟件、網(wǎng)站建設(shè)、東區(qū)網(wǎng)站維護、網(wǎng)站推廣。

實驗環(huán)境

1.安裝Python 3.7

2.安裝requests, bs4，pymysql 模塊

實驗步驟1.安裝環(huán)境及模塊

可參考https://www.jb51.net/article/194104.htm

2.編寫代碼

# 51cto 博客頁面數(shù)據(jù)插入mysql數(shù)據(jù)庫
# 導(dǎo)入模塊
import re
import bs4
import pymysql
import requests

# 連接數(shù)據(jù)庫賬號密碼
db = pymysql.connect(host='172.171.13.229',
           user='root', passwd='abc123',
           db='test', port=3306,
           charset='utf8')
# 獲取游標
cursor = db.cursor()

def open_url(url):
  # 連接模擬網(wǎng)頁訪問
  headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
           'Chrome/57.0.2987.98 Safari/537.36'}
  res = requests.get(url, headers=headers)
  return res

# 爬取網(wǎng)頁內(nèi)容
def find_text(res):
  soup = bs4.BeautifulSoup(res.text, 'html.parser')

  # 博客名
  titles = []
  targets = soup.find_all("a", class_="tit")
  for each in targets:
    each = each.text.strip()
    if "置頂" in each:
      each = each.split(' ')[0]
    titles.append(each)

  # 閱讀量
  reads = []
  read1 = soup.find_all("p", class_="read fl on")
  read2 = soup.find_all("p", class_="read fl")
  for each in read1:
    reads.append(each.text)
  for each in read2:
    reads.append(each.text)

  # 評論數(shù)
  comment = []
  targets = soup.find_all("p", class_='comment fl')
  for each in targets:
    comment.append(each.text)

  # 收藏
  collects = []
  targets = soup.find_all("p", class_='collect fl')
  for each in targets:
    collects.append(each.text)

   # 發(fā)布時間
  dates=[]
  targets = soup.find_all("a", class_='time fl')
  for each in targets:
    each = each.text.split('：')[1]
    dates.append(each)

  # 插入sql 語句
  sql = """insert into blog (blog_title,read_number,comment_number, collect, dates)
  values( '%s', '%s', '%s', '%s', '%s');"""
  # 替換頁面 \\xa0
  for titles, reads, comment, collects, dates in zip(titles, reads, comment, collects, dates):
    reads = re.sub('\\s', '', reads)
    comment = re.sub('\\s', '', comment)
    collects = re.sub('\\s', '', collects)
    cursor.execute(sql % (titles, reads, comment, collects，dates))
    db.commit()
    pass

# 統(tǒng)計總頁數(shù)
def find_depth(res):
  soup = bs4.BeautifulSoup(res.text, 'html.parser')
  depth = soup.find('li', class_='next').previous_sibling.previous_sibling.text
  return int(depth)

# 主函數(shù)
def main():
  host = "https://blog.51cto.com/13760351"
  res = open_url(host) # 打開首頁鏈接
  depth = find_depth(res) # 獲取總頁數(shù)

  # 爬取其他頁面信息
  for i in range(1, depth + 1):
    url = host + '/p' + str(i) # 完整鏈接
    res = open_url(url) # 打開其他鏈接
    find_text(res) # 爬取數(shù)據(jù)

  # 關(guān)閉游標
  cursor.close()
  # 關(guān)閉數(shù)據(jù)庫連接
  db.close()

if __name__ == '__main__':
  main()

3..MySQL創(chuàng)建對應(yīng)的表

CREATE TABLE `blog` (
 `row_id` int(11) NOT NULL AUTO_INCREMENT COMMENT '主鍵',
 `blog_title` varchar(52) DEFAULT NULL COMMENT '博客標題',
 `read_number` varchar(26) DEFAULT NULL COMMENT '閱讀數(shù)量',
 `comment_number` varchar(16) DEFAULT NULL COMMENT '評論數(shù)量',
 `collect` varchar(16) DEFAULT NULL COMMENT '收藏數(shù)量',
 `dates` varchar(16) DEFAULT NULL COMMENT '發(fā)布日期',
 PRIMARY KEY (`row_id`)
) ENGINE=InnoDB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;

4.運行代碼，查看效果:

改進版：

改進內(nèi)容：

1.數(shù)據(jù)庫里面的某些字段只保留數(shù)字即可

2.默認爬取的內(nèi)容都是字符串，存放數(shù)據(jù)庫的某些字段，最好改為整型，方便后面數(shù)據(jù)庫操作

1.代碼如下：

import re
import bs4
import pymysql
import requests

# 連接數(shù)據(jù)庫
db = pymysql.connect(host='172.171.13.229',
           user='root', passwd='abc123',
           db='test', port=3306,
           charset='utf8')
# 獲取游標
cursor = db.cursor()

def open_url(url):
  # 連接模擬網(wǎng)頁訪問
  headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
           'Chrome/57.0.2987.98 Safari/537.36'}
  res = requests.get(url, headers=headers)
  return res

# 爬取網(wǎng)頁內(nèi)容
def find_text(res):
  soup = bs4.BeautifulSoup(res.text, 'html.parser')

  # 博客標題
  titles = []
  targets = soup.find_all("a", class_="tit")
  for each in targets:
    each = each.text.strip()
    if "置頂" in each:
      each = each.split(' ')[0]
    titles.append(each)

  # 閱讀量
  reads = []
  read1 = soup.find_all("p", class_="read fl on")
  read2 = soup.find_all("p", class_="read fl")
  for each in read1:
    reads.append(each.text)
  for each in read2:
    reads.append(each.text)

  # 評論數(shù)
  comment = []
  targets = soup.find_all("p", class_='comment fl')
  for each in targets:
    comment.append(each.text)

  # 收藏
  collects = []
  targets = soup.find_all("p", class_='collect fl')
  for each in targets:
    collects.append(each.text)

  # 發(fā)布時間
  dates=[]
  targets = soup.find_all("a", class_='time fl')
  for each in targets:
    each = each.text.split('：')[1]
    dates.append(each)

  # 插入sql 語句
  sql = """insert into blogs (blog_title,read_number,comment_number, collect, dates)
  values( '%s', '%s', '%s', '%s', '%s');"""
  # 替換頁面 \\xa0
  for titles, reads, comment, collects, dates in zip(titles, reads, comment, collects, dates):
    reads = re.sub('\\s', '', reads)
    reads=int(re.sub('\\D', "", reads)) #匹配數(shù)字，轉(zhuǎn)換為整型
    comment = re.sub('\\s', '', comment)
    comment = int(re.sub('\\D', "", comment)) #匹配數(shù)字，轉(zhuǎn)換為整型
    collects = re.sub('\\s', '', collects)
    collects = int(re.sub('\\D', "", collects)) #匹配數(shù)字，轉(zhuǎn)換為整型
    dates = re.sub('\\s', '', dates)
    cursor.execute(sql % (titles, reads, comment, collects,dates))
    db.commit()
    pass

# 統(tǒng)計總頁數(shù)
def find_depth(res):
  soup = bs4.BeautifulSoup(res.text, 'html.parser')
  depth = soup.find('li', class_='next').previous_sibling.previous_sibling.text
  return int(depth)

# 主函數(shù)
def main():
  host = "https://blog.51cto.com/13760351"
  res = open_url(host) # 打開首頁鏈接
  depth = find_depth(res) # 獲取總頁數(shù)

  # 爬取其他頁面信息
  for i in range(1, depth + 1):
    url = host + '/p' + str(i) # 完整鏈接
    res = open_url(url) # 打開其他鏈接
    find_text(res) # 爬取數(shù)據(jù)

  # 關(guān)閉游標
  cursor.close()
  # 關(guān)閉數(shù)據(jù)庫連接
  db.close()

#主程序入口
if __name__ == '__main__':
  main()

2.創(chuàng)建對應(yīng)表

CREATE TABLE `blogs` (
 `row_id` int(11) NOT NULL AUTO_INCREMENT COMMENT '主鍵',
 `blog_title` varchar(52) DEFAULT NULL COMMENT '博客標題',
 `read_number` int(26) DEFAULT NULL COMMENT '閱讀數(shù)量',
 `comment_number` int(16) DEFAULT NULL COMMENT '評論數(shù)量',
 `collect` int(16) DEFAULT NULL COMMENT '收藏數(shù)量',
 `dates` varchar(16) DEFAULT NULL COMMENT '發(fā)布日期',
 PRIMARY KEY (`row_id`)
) ENGINE=InnoDB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;

3.運行代碼，驗證

升級版

為了能讓小白就可以使用這個程序，可以把這個項目打包成exe格式的文件，讓其他人，使用電腦就可以運行代碼，這樣非常方便！

1.改進代碼：

#末尾修改為：
if __name__ == '__main__':
  main()
  print("\\n\\t\\t所有數(shù)據(jù)已成功存放數(shù)據(jù)庫！!! \\n")
  time.sleep(5)

2.安裝打包模塊pyinstaller(cmd安裝）

pip install pyinstaller -i https://pypi.tuna.tsinghua.edu.cn/simple/

3.Python代碼打包

1.切換到需要打包代碼的路徑下面

2.在cmd窗口運行 pyinstaller -F test03.py （test03為項目名稱）

4.查看exe包

在打包后會出現(xiàn)dist目錄，打好包就在這個目錄里面

5.運行exe包，查看效果

檢查數(shù)據(jù)庫

相關(guān)學(xué)習(xí)推薦：mysql教程

網(wǎng)頁題目：Python爬取51cto數(shù)據(jù)并存入MySQL方法詳解
標題路徑：http://www.rwnh.cn/article40/cgcpho.html

成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián)，為您提供網(wǎng)站策劃、手機網(wǎng)站建設(shè)、小程序開發(fā)、微信公眾號、網(wǎng)站內(nèi)鏈、靜態(tài)網(wǎng)站

聲明：本網(wǎng)站發(fā)布的內(nèi)容（圖片、視頻和文字）以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主，如果涉及侵權(quán)請盡快告知，我們將會在第一時間刪除。文章觀點不代表本網(wǎng)站立場，如需處理請聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載，或轉(zhuǎn)載時需注明來源：創(chuàng)新互聯(lián)

猜你還喜歡下面的內(nèi)容

中文字幕日韩精品一区二区免费_精品一区二区三区国产精品无卡在_国精品无码专区一区二区三区_国产αv三级中文在线

Python爬取51cto數(shù)據(jù)并存入MySQL方法詳解