python爬取猫眼电影Top100榜单的信息

爬取并写入MySQL中

import pymysql
import requests
from bs4 import BeautifulSoup

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                  'Chrome/80.0.3987.163 Safari/537.36 '
}
connect = pymysql.Connect(
    host='localhost',
    port=3306,
    user='root',
    passwd='root',
    db='python',
    charset='utf8'
)
# 获取游标
cursor = connect.cursor()

def toMySQL(imgBlob, titleSQL, starringSQL, releaseTimeSQL, scoreSQL):
    print(requests.get(imgBlob).content)
    print(imgBlob)
    print(titleSQL)
    print(starringSQL[3:])
    print(releaseTimeSQL[5:])
    print(scoreSQL)

    insertSql = """INSERT INTO `python`.`maoyan`(`img`, `title`, `starring`, `release_time`, `score`) VALUES ('{a}','{b}','{c}','{d}','{e}')"""

    cursor.execute(
        insertSql.format(a=r'' + str(requests.get(imgBlob).content), b=titleSQL, c=starringSQL[3:], d=releaseTimeSQL[5:],
                         e=scoreSQL))
    print("------------------执行了插入")
    connect.commit()

def mingzihaonanqi(page):
    url = 'https://maoyan.com/board/4?offset=' + str(page)
    res = requests.get(url, headers=headers)
    # 页面session失效, 需要重新验证, 打印出来方便使用
    print(res.url)
    # 打印出页面的所有代码
    # print(res.text)
    soup = BeautifulSoup(res.text, 'html.parser')
    ResultSets = soup.find_all('dd')

    for resultSet in ResultSets:
        tag = resultSet
        soupTag = BeautifulSoup(str(tag), 'html.parser')
        Title = soupTag.find('a').get('title')
        imgSrc = soupTag.find('img', class_='board-img').get('data-src')
        starring = soupTag.find('p', class_='star').text.strip()
        releaseTime = soupTag.find('p', class_='releasetime').text.strip()
        score = soupTag.find('p', class_='score').text.strip()
        toMySQL(imgSrc, Title, starring, releaseTime, score)
        print(str(page) + "----------")

if __name__ == '__main__':
    for i in range(30, 100, 10):
        print(i)  # 0 10 20 ````
        mingzihaonanqi(i)

库表信息

运行结果:

爬取后写入MongoDB

import pymongo
import requests
from bs4 import BeautifulSoup

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                  'Chrome/80.0.3987.163 Safari/537.36 '
}

def toMongoDB(imgSrc, Title, starring, releaseTime, score):
    print(imgSrc)
    print(Title)
    print(starring[3:])
    print(releaseTime[5:])
    print(score)

    myClient = pymongo.MongoClient("mongodb://localhost:27017/")
    myDb = myClient["maoyan"]
    myCollection = myDb["maoyanTop100"]
    myDictionary = {
        "imgSrc": imgSrc,
        "Title": Title,
        "starring": starring[3:],
        "releaseTime": releaseTime[5:],
        "score": score
    }
    result = myCollection.insert_one(myDictionary)
    print(result)
    pass

def mingzihaonanqi(page):
    url = 'https://maoyan.com/board/4?offset=' + str(page)
    res = requests.get(url, headers=headers)
    # 页面session失效, 需要重新验证, 打印出来方便使用
    print(res.url)
    # 打印出页面的所有代码
    # print(res.text)
    soup = BeautifulSoup(res.text, 'html.parser')
    ResultSets = soup.find_all('dd')

    for resultSet in ResultSets:
        tag = resultSet
        soupTag = BeautifulSoup(str(tag), 'html.parser')
        Title = soupTag.find('a').get('title')
        imgSrc = soupTag.find('img', class_='board-img').get('data-src')
        starring = soupTag.find('p', class_='star').text.strip()
        releaseTime = soupTag.find('p', class_='releasetime').text.strip()
        score = soupTag.find('p', class_='score').text.strip()
        # 写入MongoDB
        toMongoDB(imgSrc, Title, starring, releaseTime, score)
        print(str(page) + "----------")

if __name__ == '__main__':
    for i in range(0, 100, 10):
        print(i)  # 0 10 20 ````
        mingzihaonanqi(i)

运行结果