爬虫实操

爬取四大名著之《三国演义》

三国演义地址

productor

import requests

res = requests.get("https://www.shicimingju.com/book/sanguoyanyi.html")

with open('text.html',mode='wb') as fw:
    for line in res.iter_content():
        fw.write(line)

customer

from bs4 import BeautifulSoup
import requests

soup = BeautifulSoup(open('text.html'), 'lxml')

download_info = (
    {
        'title': li.text,
        'link': 'https://www.shicimingju.com' + li.find('a').attrs.get('href')
    }
    for li in soup.find(class_='book-mulu').find_all(name='li')
)

for item in download_info:
    article_soup = BeautifulSoup(requests.get(item.get('link', None)).text, 'lxml')
    article_div = article_soup.find(class_='bookmark-list')
    with open('sgyy.txt', mode='ab+') as fw:
        title = article_div.find(name='h1').text
        content = article_div.find(class_='chapter_content').text
        fw.write((title + '
' + content + '
').encode('utf-8'))

效果图

爬取上海市的肯德基门店信息

上海市肯德基门店

productor

import requests

res = requests.get("http://www.kfc.com.cn/kfccda/storelist/index.aspx")

with open('text2.html',mode='wb') as fw:
    for line in res.iter_content():
        fw.write(line)

customer

import requests
import json

header = {
    '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',
    'Referer': 'http://www.kfc.com.cn/kfccda/storelist/index.aspx',
}

res = requests.post(
    "http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx",
    params={
        'op': 'cname'
    },
    data={
        'cname': '上海',
        'pid': '',
        'keyword':'',
        'pageIndex': 1,
        'pageSize': 500
    },
    headers=header
)

kfc_info = json.loads(res.text).get('Table1')
kfc_list = [
    {
        "storeName":kfc.get('storeName')+'餐厅',
        "addressDetail":kfc.get("addressDetail"),
        "pro":kfc.get("pro")
    }
    for kfc in kfc_info
]

print(kfc_list)
print(len(kfc_list)) #455