Python學習（爬蟲學習）

1、爬取電影
import requests
from bs4 import BeautifulSoup
import re
import pandas

headers = {
‘Host’: ‘movie.douban.com’,
‘Origin’: ‘movie.douban.com’,
‘User-Agent’: ‘Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Mobile Safari/537.36’,
}
base_url = ‘https://movie.douban.com/top250?start={}&filter=’

response = requests.get(‘https://movie.douban.com/top250?start=0&filter=’, headers=headers)
if response.status_code == 200:
# print(response.text)
pass

pattern1 = re.compile(’<div.?class=“item”>.?<div.?class=“pic”>.?<a.?href="(.?)">’,
re.S) # 去掉所有換行符，並用正則表達式去匹配每一個頁面的具體電影
urls = re.findall(pattern1, response.text)

directors = [] # 導演

names = [] # 電影名

stars = [] # 主演

countrys = [] # 電影的出產地

languages = [] # 電影語言

headers_urls = {
‘Host’: ‘movie.douban.com’,
‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36’
}

肖申克的救贖 The Shawshank Redemption

弗蘭克·德拉邦特

蒂姆·羅賓斯

def base_urls(base_url):
urls = []
# 這裏我們只能前兩頁做測試，所以range只設置到了50
# for i in range(0, 275, 25):
# true_url = base_url.format(i)
# print(true_url)
for i in range(0, 50, 25):
true_url = base_url.format(i)
print(true_url)

    response = requests.get(true_url, headers=headers)
    if response.status_code == 200:
        # print(response.text)

        pattern1 = re.compile('<div.*?class="item">.*?<div.*?class="pic">.*?<a.*?href="(.*?)">', re.S)
        # 去掉所有換行符，並用正則表達式去匹配每一個頁面的具體電影
        url = re.findall(pattern1, response.text)
        # 因爲這裏是用findall，他返回的是一個列表，如果我們直接append，會導致列表嵌套，故我們這裏用個for循環提取出列表的元素再append進去

        for i in url:
            urls.append(i)

return urls

def parse_url(urls):
# 因爲只拿前兩頁做測試，所以range設置到50
for i in range(0, 50, 1):
res = requests.get(urls[i], headers=headers_urls)
print(res)
if res.status_code == 200:
soup = BeautifulSoup(res.text, ‘lxml’)
# 爬取電影名
name = (soup.find(‘span’, property=“v:itemreviewed”))
names.append(name.string)
# print(names)

        # 爬取導演
        director = soup.find('a', rel="v:directedBy")
        directors.append(director.string)
        # print(director.text)

        # 爬取明星
        star_save = []
        for star in soup.find_all('a', rel="v:starring"):
            star_save.append(star.text)
            stars.append(star_save)
        # print(stars)

        # 爬取製片國家
        # <span class="pl">製片國家/地區:</span> 美國<br>
        # 學到的知識點：通過匹配文本內容找下個兄弟節點
        country = soup.find('span', text='製片國家/地區:').next_sibling[1:]
        countrys.append(country)
        # print(countrys)

        # 爬取影片語言
        # <span class="pl">語言:</span>
        language = soup.find('span', text='語言:').next_sibling[1:]
        languages.append(language)
        # print(language)

print(directors)

print(true_director)

print(a)

if name == ‘main’:
base = base_urls(base_url)
print(base)
print(len(base))
parse_url(base)
print(countrys)
print(directors)
print(languages)
print(names)
#
# 最後我們將數據寫入到一個excel表格裏
info = {‘Filmname’: names, ‘Directors’: directors, ‘Country’: countrys, ‘Languages’: languages}
pdfile = pandas.DataFrame(info)

pdfile.to_excel('DoubanFilm.xlsx', sheet_name="豆瓣電影")

2、爬取房價
import requests
import bs4

def open_url(url):
headers={“user-agent”:“Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36”}
res=requests.get(url,headers=headers)

return res

def find_data(res):
soup=bs4.BeautifulSoup(res.text,“html.parser”)
content=soup.find(id=“Cnt-Main-Article-QQ”)
#print(content)
target=content.find_all(“p”,style=“TEXT-INDENT: 2em”)

for each in target:
    print(each.text)

def main():
url=“https://news.house.qq.com/a/20170702/003985.htm”
res=open_url(url)
find_data(res)
# with open(“test.txt”,“w”,encoding=“utf-8”) as file:
# file.write(res.text)

if name==“main”:
main()
結果圖：

3、 生成表格（表格出了，沒數據）
import requests
import bs4
import openpyxl

def open_url(url):
headers={“user-agent”:“Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36”}
res=requests.get(url,headers=headers)

return res

def find_data(res):
data=[]
soup=bs4.BeautifulSoup(res.text,“html.parser”)
content=soup.find(id=“Cnt-Main-Article-QQ”)
#print(content)
target=content.find_all(“p”,style=“TEXT-INDENT: 2em”)
target=iter(target)

for each in target:
    #print(each.text)
    if each.text.isnumeric():
        data.append([
            re.search(r'\[(.+)\]',next(target).text).group(1),
            re.search(r'\d.*',next(target).text).group(),
            re.search(r'\d.*',next(target).text).group(),
            re.search(r'\d.*',next(target).text).group()])

    return data

def to_excel(data):
wb=openpyxl.Workbook()
wb.guess_types=True
ws=wb.active
ws.append([‘城市’,‘平均房價’,‘平均工資’,‘房價工資比’])
for each in data:
ws.append(each)

wb.save("2017年中國主要城市房價工資比排行榜.xlsx")

def main():
url=“https://news.house.qq.com/a/20170702/003985.htm”
res=open_url(url)
data=find_data(res)
to_excel(data)
# with open(“test.txt”,“w”,encoding=“utf-8”) as file:
# file.write(res.text)

if name==“main”:
main()