Python爬虫

发表于 | 分类于

1、爬取豆瓣Top250电影

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
#------------------------------------
# !/usr/bin/env python
# -*- encoding: utf-8 -*-
# @FileName   :   豆瓣Top250.py
# @Author     :   嘿嘿嘿
# @Time       :   2020/7/19 0:11
# @Software   :   PyCharm
#------------------------------------

from bs4 import BeautifulSoup           #网页解析，获取数据
import re                               #正则表达式，进行文字匹配
import urllib.request,urllib.error      #指定URL，获取网页数据
import xlwt                             #进行excel操作
import sqlite3                          #进行数据库操作

def main():
    baseurl = "https://movie.douban.com/top250?start="
    datalist = getData(baseurl)
    savepath = ".\\豆瓣电影Top250.xls"
    saveDate(datalist, savepath)

# 获取网页
def getData(baseurl):
    datalist = []
    for i in range(0, 10):
        url = baseurl + str(i*25)
        html = askURL(url)
        soup = BeautifulSoup(html, 'html.parser')
        for item in soup.find_all('div',class_="item"):
            data = []
            item = str(item)
            id = re.findall('<em class="">(.*)</em>', item)[0]
            title = re.findall(r'<span class="title">(.*)</span>', item)[0]
            link = re.findall(r'<a href="(.*)">', item)[0]
            rating_num = re.findall(r'<span class="rating_num" property="v:average">(.*)</span>', item)[0]
            people = re.findall(r'<span>(.*人评价)</span>', item)[0]
            data.append(id)
            data.append(title)
            data.append(rating_num)
            data.append(link)
            data.append(people)
            datalist.append(data)
    print(datalist)
    return datalist

def askURL(url):
    head = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36"
    }
    request = urllib.request.Request(url, headers=head)
    html = ''
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode('utf-8')
        #print(html)
    except urllib.error.URLError as e:
        if hasattr(e, 'code'):
            print(e.code)
        if hasattr(e, 'reason'):
            print(e.reason)
    return html

# 保存数据
def saveDate(datalist, savepath):
    workbook = xlwt.Workbook(encoding='utf-8', style_compression=0)
    worksheet = workbook.add_sheet('sheet1', cell_overwrite_ok=True)
    col = ("电影排名", "电影名称", "电影评分", "评价人数")
    for i in range(0, 4):
        worksheet.write(0, i, col[i])
    for i in range(0,250):
        for j in range(0,5):
            worksheet.write(i+1,j,datalist[i][j])
    workbook.save('豆瓣Top250.xls')

if __name__ == "__main__":

2、爬取江西高考投档线

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
#------------------------------------
# !/usr/bin/env python
# -*- encoding: utf-8 -*-
# @FileName   :   江西高考投档线.py
# @Author     :   嘿嘿嘿
# @Time       :   2020/7/19 14:49
# @Software   :   PyCharm
#------------------------------------
from bs4 import BeautifulSoup           #网页解析，获取数据
import re                               #正则表达式，进行文字匹配
import urllib.request,urllib.error      #指定URL，获取网页数据
import xlwt                             #进行excel操作

def main():
    baseurl = "https://www.dxsbb.com/news/58588.html"
    datalist = getData(baseurl)
    saveDate(datalist)

# 获取网页
def getData(baseurl):
    title_col = [['序号'], ['科类'], ['院校代号'], ['院校名称'], ['投档线'], ['最低投档排名']]
    datas = ['']
    datalist = []
    html = askURL(baseurl)
    soup = BeautifulSoup(html, 'html.parser')
    for item in soup.find_all('td', style="text-align:center;"):
        item = str(item).strip()
        data = re.findall(r'<td style="text-align:center;">(.*)</td>', item)
        data = str(data)
        data = re.sub(r"<a class=.keyWord. href=.../news/list_...?.html. target=._blank.>", '', data)
        data = re.sub(r"</a>", '', data)
        data = str(data).strip("['")
        data = str(data).strip("']")
        print(data)
        datas.append(data)
        if len(datas)%6 == 0:
            datas = []
            datalist.append(datas)
    datalist[0] = title_col
    datalist.pop()
    return datalist

def askURL(url):
    head = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36"
    }
    request = urllib.request.Request(url, headers=head)
    html = ''
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode('gbk')
    except urllib.error.URLError as e:
        if hasattr(e, 'code'):
            print(e.code)
        if hasattr(e, 'reason'):
            print(e.reason)
    return html

# 保存数据
def saveDate(datalist):
    workbook = xlwt.Workbook(encoding='utf-8', style_compression=0)
    worksheet = workbook.add_sheet('sheet1', cell_overwrite_ok=True)
    for i in range(0, len(datalist)):
        for j in range(0, 6):
            worksheet.write(i, j, datalist[i][j])
    workbook.save('2019江西高考二本投档线.xls')

if __name__ == "__main__":