urllib.request.urlretrieve可以根據文件的URL下載文件：

# -*- coding: utf-8 -*-
from urllib.request import urlretrieve
from urllib.request import urlopen
from bs4 import BeautifulSoup


html = urlopen("http://www.pythonscraping.com/")
bsObj = BeautifulSoup(html, "lxml")
imageLocation = bsObj.find("a", {"id":"logo"}).find("img")["src"]
#print(imageLocation)
urlretrieve(imageLocation, "logo.jpg")

這段程序從 http://pythonscraping.com下載logo圖片，然後在程序運行的文件夾裏保存為logo.jpg文件。

下面的程序會把 http://pythonscraping.com 主頁上所有src屬性且圖片後綴為.jpg的文件都下載下來：

# -*- coding: utf-8 -*-
import os
from urllib.request import urlretrieve
from urllib.request import urlopen
from bs4 import BeautifulSoup


downloadDirectory = "downloaded"
baseUrl = "http://pythonscraping.com"

def getAbsoluteURL(baseUrl, source):
    if source.startswith("http://www."):
        url = "http://"+source[11:]
    elif source.startswith("http://"):
        url = source
    elif source.startswith("www."):
        url = source[4:]
        url = "http://"+source
    else:
        url = baseUrl+"/"+source
    if baseUrl not in url:
        return None
    return url
    
def getDownloadPath(baseUrl, absoluteUrl, downloadDirectory):
    path = absoluteUrl.replace("www.", "")
    path = path.replace(baseUrl, "")
    path = downloadDirectory + path
    if path.endswith(".jpg"):
        directory = os.path.dirname(path)
        
        if not os.path.exists(directory):
            os.makedirs(directory)
        #print(path)
        return path
    
html = urlopen("http://www.pythonscraping.com")
bsObj = BeautifulSoup(html, "lxml")
downloadList = bsObj.findAll(src=True)

for download in downloadList:
    #print(download["src"])
    fileUrl = getAbsoluteURL(baseUrl, download["src"])
    if fileUrl is not None:
        print(fileUrl)
        urlretrieve(fileUrl, getDownloadPath(baseUrl, fileUrl, downloadDirectory))

2、

# -*- coding: utf-8 -*-
import csv

csvFile = open("test.csv", 'w+')
try:
    writer = csv.writer(csvFile)
    writer.writerow(('number', 'number plus 2', 'number times 2'))
    for i in range(10):
        writer.writerow( (i, i+2, i*2))
finally:
    csvFile.close()

運行以上代碼後，你會看到一個CSV文件：

獲取維基百科詞條中的HTML表格並寫入CSV文件。

# -*- coding: utf-8 -*-
import csv
from urllib.request import urlopen
from bs4 import BeautifulSoup


html = urlopen("http://en.wikipedia.org/wiki/Comparison_of_text_editors")
bsObj = BeautifulSoup(html, "lxml")
# 主對比表格是當前頁面上的第一個表格
table = bsObj.findAll("table",{"class":"wikitable"})[0]
rows = table.findAll("tr")

csvFile = open("editors.csv", 'wt', newline="", encoding='utf-8')
writer = csv.writer(csvFile)
try:
    for row in rows:
        csvRow = []
        for cell in row.findAll(['td', 'th']):
            csvRow.append(cell.get_text())
        writer.writerow(csvRow)
finally:
    csvFile.close()

《Python網絡數據采集》讀書筆記（六）