Python Learning

# Install the Autoscraper !pip install autoscraper

# Example 1 from autoscraper import AutoScraper url = 'https://github.com/SurendraRedd?tab=repositories' fetch_list = ['Notebooks'] scraper = AutoScraper() result = scraper.build(url=url, wanted_list=fetch_list) scraper.get_result_similar(url, grouped=True)

# Example 2 from autoscraper import AutoScraper url = 'https://finance.yahoo.com/quote/AAPL/?guccounter=1' fetch_list = ['Previous Close', '131.94'] scraper = AutoScraper() result = scraper.build(url=url, wanted_list=fetch_list) scraper.get_result_similar(url, grouped=True)

# save the rules and search scraper.set_rule_aliases({'rule_ae2u': 'price','rule_ivlb': 'Names'}) scraper.keep_rules(['rule_ae2u', 'rule_ivlb']) scraper.save('AppleSearch') # Note rule values will need to be updated every time based on the execution.

# Try the above rules in another url Amz_Url = 'https://finance.yahoo.com/quote/AMZN?p=AMZN' scraper.get_result_similar(Amz_Url, group_by_alias=True)

# Example 2 from autoscraper import AutoScraper url = 'https://www.amazon.in/s?k=dell+laptops&ref=nb_sb_noss_2' fetch_list = ['₹51,499','Dell Inspiron 5406 14" FHD Display 2in1 Laptop (11th Gen i3-1115G4 / 4GB / 256GB SSD / Integrated Graphics/ Win 10 + MS Office / Backlit with FPR / Platinum Silver) D560446WIN9S','10'] scraper = AutoScraper() result = scraper.build(url=url, wanted_list=fetch_list)

#scraper.get_result_similar(url, group_by_alias=True) scraper.get_result_similar(url, grouped=True) # Note: Sometimes Duplicate rule values will be displayed

# save the rules and search scraper.set_rule_aliases({'rule_ot4i': 'price','rule_konw': 'Names'}) scraper.keep_rules(['rule_ot4i', 'rule_konw']) scraper.save('DellLaptopSearch')

# Try the above rules in another url HP_Url = 'https://www.amazon.in/s?k=HP+laptops&ref=nb_sb_noss_2' scraper.get_result_similar(HP_Url, group_by_alias=True)

# Example 3 from autoscraper import AutoScraper url = 'https://stackoverflow.com/questions/2081586/web-scraping-with-python' # We can add one or multiple candidates here. # You can also put urls here to retrieve urls. wanted_list = ["What are metaclasses in Python?"] scraper = AutoScraper() result = scraper.build(url, wanted_list) print(result)

scraper.get_result_similar('https://stackoverflow.com/questions/606191/convert-bytes-to-a-string')