快捷導(dǎo)航

Python如何爬取51cto數(shù)據(jù)并存入MySQL

更新時(shí)間：2020年08月25日 11:18:17 作者：Keep__Studying

這篇文章主要介紹了Python如何爬取51cto數(shù)據(jù)并存入MySQL,文中通過(guò)示例代碼介紹的非常詳細(xì)，對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友可以參考下

實(shí)驗(yàn)環(huán)境

1.安裝Python 3.7

2.安裝requests, bs4，pymysql 模塊

實(shí)驗(yàn)步驟1.安裝環(huán)境及模塊

可參考http://www.dbjr.com.cn/article/194104.htm

2.編寫(xiě)代碼

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

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

def open_url(url):
  # 連接模擬網(wǎng)頁(yè)訪問(wèn)
  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(yè)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(píng)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(shí)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(yǔ)句
  sql = """insert into blog (blog_title,read_number,comment_number, collect, dates)
  values( '%s', '%s', '%s', '%s', '%s');"""
  # 替換頁(yè)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(jì)總頁(yè)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(kāi)首頁(yè)鏈接
  depth = find_depth(res) # 獲取總頁(yè)數(shù)

  # 爬取其他頁(yè)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(kāi)其他鏈接
    find_text(res) # 爬取數(shù)據(jù)

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

if __name__ == '__main__':
  main()

3..MySQL創(chuàng)建對(duì)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(biāo)題',
 `read_number` varchar(26) DEFAULT NULL COMMENT '閱讀數(shù)量',
 `comment_number` varchar(16) DEFAULT NULL COMMENT '評(píng)論數(shù)量',
 `collect` varchar(16) DEFAULT NULL COMMENT '收藏?cái)?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(yùn)行代碼，查看效果:

改進(jìn)版：

改進(jìn)內(nèi)容：

1.數(shù)據(jù)庫(kù)里面的某些字段只保留數(shù)字即可

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

1.代碼如下：

import re
import bs4
import pymysql
import requests

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

def open_url(url):
  # 連接模擬網(wǎng)頁(yè)訪問(wèn)
  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(yè)內(nèi)容
def find_text(res):
  soup = bs4.BeautifulSoup(res.text, 'html.parser')

  # 博客標(biāo)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(píng)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(shí)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(yǔ)句
  sql = """insert into blogs (blog_title,read_number,comment_number, collect, dates)
  values( '%s', '%s', '%s', '%s', '%s');"""
  # 替換頁(yè)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(jì)總頁(yè)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(kāi)首頁(yè)鏈接
  depth = find_depth(res) # 獲取總頁(yè)數(shù)

  # 爬取其他頁(yè)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(kāi)其他鏈接
    find_text(res) # 爬取數(shù)據(jù)

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

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

2.創(chuàng)建對(duì)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(biāo)題',
 `read_number` int(26) DEFAULT NULL COMMENT '閱讀數(shù)量',
 `comment_number` int(16) DEFAULT NULL COMMENT '評(píng)論數(shù)量',
 `collect` int(16) DEFAULT NULL COMMENT '收藏?cái)?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(yùn)行代碼，驗(yàn)證

升級(jí)版

為了能讓小白就可以使用這個(gè)程序，可以把這個(gè)項(xiàng)目打包成exe格式的文件，讓其他人，使用電腦就可以運(yùn)行代碼，這樣非常方便！

1.改進(jìn)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(kù)！!! \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(yùn)行 pyinstaller -F test03.py （test03為項(xiàng)目名稱）

4.查看exe包

在打包后會(huì)出現(xiàn)dist目錄，打好包就在這個(gè)目錄里面

5.運(yùn)行exe包，查看效果

檢查數(shù)據(jù)庫(kù)

總結(jié)：

1.這一篇博客，是在上一篇的基礎(chǔ)上改進(jìn)的，步驟是先爬取首頁(yè)的信息，再爬取其他頁(yè)面信息，最后在改進(jìn)細(xì)節(jié)，打包exe文件

2.我們爬取網(wǎng)頁(yè)數(shù)據(jù)大多數(shù)還是存放到數(shù)據(jù)庫(kù)的，所以這種方法很實(shí)用。

3.其實(shí)在此博客的基礎(chǔ)上還是可以改進(jìn)的，重要的是掌握方法即可。

以上就是本文的全部?jī)?nèi)容，希望對(duì)大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章:

欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

Python如何爬取51cto數(shù)據(jù)并存入MySQL

相關(guān)文章

最新評(píng)論

大家感興趣的內(nèi)容

最近更新的內(nèi)容

常用在線小工具