cmoncrawl.processor.extraction.utils#

Functions

all_same_transform(dict, fc)

chain_transforms(trans)

check_required(required_fields, extractor_name)

combine_dicts(dicts)

extract_transform(tag, extract_dict, ...)

get_attribute_transform(attr_name)

get_tag_transform(tag_desc)

get_tags_transform(tag_desc)

get_text_list_transform([sep])

get_text_transform(tag[, recursive])

transform(dict, transforms)