3 examples of 'python google search' in Python

15
def google_search(query, limit):
16
    global last
17
    ret_url_list = list()
18
19
    for tries in range(1, 10):
20
        try:
21
            if last:
22
                 sleep(int(60 - (clock() - last)))
23
        except ValueError:
24
            pass
25
26
        last = clock()
27
28
        try:
29
            for url in google_web_search(query, stop=limit):
30
                if 'youtube.com/watch?v=' in url:
31
                    ret_url_list.append(url.split('&')[0])
32
33
        except KeyboardInterrupt:
34
            raise
35
36
        except HTTPError as e:
37
            print('google search service unavailable.')
38
39
            if tries > 3:
40
                print('Failed to download google search result. Reason: ' + str(e))
41
                raise
42
43
            print('Failed to download google search result, retrying. Reason: ' + str(e))
44
            sleep(1)
45
46
        except:
47
            e = sys.exc_info()[0]
48
            if tries > 3:
49
                print('Failed to download google search result. Reason: ' + str(e))
50
                raise
51
52
            print('Failed to download google search result, retrying. Reason: ' + str(e))
53
            sleep(1)
54
        else:
55
            break
56
57
    return ret_url_list[:limit]

11
def google_search(keywords: str) -> List[Dict[str, str]]:
12
    query = {'q': keywords}
13
    # Gets the page
14
    page = requests.get('http://www.google.com/search', params=query)
15
    # Parses the page into BeautifulSoup
16
    soup = BeautifulSoup(page.text, "lxml")
17
18
    # Gets all search URLs
19
    anchors = soup.find(id='search').findAll('a')
20
    results = []
21
22
    for a in anchors:
23
        try:
24
            # Tries to get the href property of the URL
25
            link = a['href']
26
        except KeyError:
27
            continue
28
        # Link must start with '/url?', as these are the search result links
29
        if not link.startswith('/url?'):
30
            continue
31
        # Makes sure a hidden 'cached' result isn't displayed
32
        if a.text.strip() == 'Cached' and 'webcache.googleusercontent.com' in a['href']:
33
            continue
34
        # a.text: The name of the page
35
        result = {'url': "https://www.google.com{}".format(link),
36
                  'name': a.text}
37
        results.append(result)
38
    return results

13
def __init__(self, query='hello world', num=10, start=0, recent=None, site='', pages=1, sleep=True):
14
    self.query = '+'.join(query.split(' '))
15
    self.num = num
16
    self.start = start
17
    self.recent = recent
18
    self.site = site
19
    self.pages = pages
20
    self.sleep = sleep
21
    self.headers = {'user-agent': 'Mozilla/5.0'}
22
    self.big_soup = BeautifulSoup("", 'html.parser')