10 examples of 'python download pdf from url' in Python

7
def download(url):
8
    wget.download(url)

5
def download(url, file_name):
6
    res = requests.get(url, stream=True)
7
    if res.status_code == 200:
8
        with open(file_name, 'wb') as file:
9
            for chunk in res.iter_content(chunk_size=1024):
10
                file.write(chunk)

19
def download_2(url):
20
    try:
21
        response = requests.get(url)
22
    except Exception:
23
        print('Failed Download!')
24
    else:
25
        if response.status_code == 200:
26
            with open('file_name.jpg', 'wb') as f:
27
                f.write(requests.get(url).content)
28
                print("Succesfully Downloaded")
29
        else:
30
            print('Failed Download!')

151
def _download(url, directory, filename):
152
    try:
153
        with urllib.request.urlopen(url) as response, open(
154
            os.path.join(directory, filename), "wb"
155
        ) as out_file:
156
            shutil.copyfileobj(response, out_file)
157
    except urllib.error.HTTPError as exception:
158
        sys.stderr.write(str(exception))

10
def _download(url, path):
11
    """Download *url* to *path*."""
12
    r = requests.get(url.strip(), stream=True)
13
    with open(str(path), 'wb') as f:
14
        for chunk in r.iter_content(chunk_size=1024):
15
            # filter out keep-alive new chunks
16
            if chunk:
17
                f.write(chunk)

16
def download_page(url):
17
    try:
18
        headers = {}
19
        headers['User-Agent'] = "Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.27 Safari/537.17"
20
        req = urllib.request.Request(url, headers = headers)
21
        resp = urllib.request.urlopen(req)
22
        respData = str(resp.read())
23
        return respData
24
    except Exception as e:
25
        print(str(e))

109
def download_urllib(url, filename):
110
    """ Try to donwload via urllib."""
111
    print("Trying to Download via urllib from:\n  ", url)
112
    keep_going = True
113
    try:
114
        url_res = urllib2.urlopen(url)
115
    except (HTTPError, URLError, ssl.CertificateError) as err:
116
        print("Error: %s" % err)
117
        return False
118
    with open(filename, 'wb') as outfile:
119
        block_sz = 8192
120
        meta = url_res.info()
121
        meta_func = meta.getheaders if hasattr(meta, 'getheaders') else meta.get_all
122
        meta_length = meta_func("Content-Length")
123
        file_size = None
124
        if meta_length:
125
            file_size = int(meta_length[0])
126
        message = "Downloading: {0}\nBytes: {1}\n".format(url, file_size)
127
        dstyle = wx.PD_APP_MODAL | wx.PD_CAN_ABORT | wx.PD_AUTO_HIDE
128
        if file_size:
129
            progress = wx.ProgressDialog('Downloading', message,
130
                                         maximum=1+file_size/block_sz, style=dstyle)
131
        else:
132
            progress = wx.ProgressDialog('Downloading', message, style=dstyle)
133
134
        file_size_dl = 0
135
        while keep_going:
136
            read_buffer = url_res.read(block_sz)
137
            if not read_buffer:
138
                progress.Update(file_size_dl / block_sz, "message+\nDONE!")
139
                wx.Sleep(0.2)
140
                break
141
142
            file_size_dl += len(read_buffer)
143
            outfile.write(read_buffer)
144
145
            status = "{0:16}".format(file_size_dl)
146
            if file_size:
147
                status += "   [{0:6.2f}%]".format(file_size_dl * 100 / file_size)
148
            (keep_going, dummy_skip) = progress.Update(file_size_dl / block_sz,
149
                                                       message+status)
150
            wx.Sleep(0.08)  # Give the GUI some update time
151
        progress.Destroy()

58
def download(self, url):
59
    '''
60
    下载指定url页面
61
    :param url:
62
    :return:
63
    '''
64
    headers = {
65
        'User-Agent': useragent.getUserAgent()
66
    }
67
    s = requests.session()
68
    r = s.request(method='get', url=url, headers=headers)
69
    if r.status_code == 200:
70
        print('正在抓取地址:%s' % url)
71
        print('User-Agent:', r.request.headers.get('user-agent'))
72
        return r.content
73
    return None

9
def download_file(url):
10
    ''' Downloads and extracts the url content.
11
12
       :kwarg url: Contains the download link to raw data.
13
14
    '''
15
    response = requests.get(url, stream = True)
16
    with open('subtitle.zip', 'wb') as out_file:
17
        fsrc = response.raw
18
        size = response.headers.get("content-length")
19
        length = 16*1024
20
        while True:
21
            buf = fsrc.read(length)
22
            if not buf:
23
                break
24
            out_file.write(buf)
25
            sys.stdout.write("Downloaded " + str(os.path.getsize('subtitle.zip')/1024) + "kb of " + str(int(size)/1024) + " kb\r")
26
            sys.stdout.flush()
27
        print "\nDownload complete\nExtracting"
28
    del response
29
    try:
30
        zipfile.ZipFile.extractall(zipfile.ZipFile('subtitle.zip'))
31
        os.remove('subtitle.zip')
32
    except:
33
        print "* The subtitle file is not good to extract."
34
        return 'no'
35
    return prompt()

18
def download_file(url, download_path):
19
20
    local_filename = url.split('/')[-1]
21
    if not isfile(join(download_path, local_filename)):
22
        # NOTE the stream=True parameter
23
        r = requests.get(url, stream=True)
24
        with open(join(download_path, local_filename), 'wb') as f:
25
            for chunk in r.iter_content(chunk_size=1024):
26
                if chunk: # filter out keep-alive new chunks
27
                    f.write(chunk)
28
                    f.flush()
29
        print local_filename